Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to the consequences of actions or events, particularly in legal and medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The neuron detects verbs that indicate a causal relationship, particularly focusing on words like "result," "lead," "comes," and "associated" that link causes to effects.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    medical or scientific terminology related to biological processes and medical conditions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     Económica
    -0.68
     Pristup
    -0.63
     Matos
    -0.62
    AsNil
    -0.59
     beginnetje
    -0.58
    ſelben
    -0.58
     Redacción
    -0.57
     Constitucional
    -0.56
     Capacidad
    -0.56
     дописавши
    -0.56
    POSITIVE LOGITS
    ftagPool
    0.35
    AddTagHelper
    0.35
     nahilalakip
    0.34
     aapt
    0.34
    AddHtmlAttribute
    0.32
    <?
    0.31
    addGap
    0.30
    rog
    0.30
    verifyException
    0.29
     surla
    0.29
    Act Density 1.878%

    No Known Activations