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

    Neuronpedia

    INDEX
    Explanations

    verbs in the past participle form

    oai_token-act-pair · gpt-3.5-turbo

    phrases beginning with "by" indicating actions or attributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izons
    -0.88
    ISE
    -0.82
    utical
    -0.74
    results
    -0.73
    growth
    -0.72
    aic
    -0.72
    utics
    -0.72
    ESE
    -0.71
    Limited
    -0.70
    rued
    -0.69
    POSITIVE LOGITS
     tweeting
    1.46
     ordering
    1.35
     stabbing
    1.28
     announcing
    1.28
     declaring
    1.27
     posting
    1.26
     assaulting
    1.26
     murdering
    1.26
     deleting
    1.25
     slamming
    1.25
    Act Density 0.261%

    No Known Activations