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

    Neuronpedia

    INDEX
    Explanations

    words related to irreversibility or irreparability

    oai_token-act-pair · gpt-3.5-turbo

    words related to irrelevance or lack of importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     commencement
    -0.68
     Holder
    -0.65
     buckle
    -0.65
     handle
    -0.64
     cheers
    -0.63
     sheet
    -0.62
     Bulldogs
    -0.61
    auri
    -0.60
     dispatch
    -0.59
     Dwell
    -0.59
    POSITIVE LOGITS
    voc
    1.64
    parable
    1.59
    vers
    1.28
    cover
    1.24
    medi
    1.22
    lev
    1.22
    con
    1.20
    place
    1.20
    ve
    1.14
    putable
    1.14
    Act Density 0.030%

    No Known Activations