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

    Neuronpedia

    INDEX
    Explanations

    political terms and proper nouns related to influential figures

    oai_token-act-pair · gpt-3.5-turbo

    words related to political themes and controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icularly
    -0.91
    umin
    -0.90
    ework
    -0.88
    ettes
    -0.87
    clud
    -0.85
    estyles
    -0.85
    oso
    -0.85
    eteenth
    -0.84
    aceous
    -0.82
    iard
    -0.80
    POSITIVE LOGITS
     Passage
    0.86
     ank
    0.76
    OWN
    0.71
    uyomi
    0.70
    APE
    0.68
     Seas
    0.66
    rouse
    0.64
    é¾įå¥ij士
    0.63
     Goldstein
    0.62
     Downs
    0.61
    Act Density 0.025%

    No Known Activations