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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating presence or emphasis on specific conditions or factors related to health or performance

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

    scientific and medical terminology related to research, clinical trials, and experimental methods.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    the word "in" at the beginning of phrases or clauses in technical and scientific documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    ostante
    -0.37
    neath
    -0.35
    +:+
    -0.35
    Hentet
    -0.33
    GETHER
    -0.33
    zugehen
    -0.32
     dàng
    -0.30
    RunWith
    -0.28
    cels
    -0.28
    fraid
    -0.28
    POSITIVE LOGITS
    rungsseite
    0.75
     Италијани
    0.69
     defaultstate
    0.65
     autorytatywna
    0.63
     betweenstory
    0.62
     disponibilités
    0.60
     '\\;'
    0.60
    ⅘
    0.60
    ArrowToggle
    0.59
    uxxxx
    0.59
    Act Density 0.590%

    No Known Activations