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

    Neuronpedia

    INDEX
    Explanations

    references to proposed legislation and specific policy measures

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating legislative proposals or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chal
    -0.74
    Ti
    -0.69
     Corpus
    -0.64
     Diet
    -0.64
     Tuc
    -0.64
    Statistics
    -0.63
     Vis
    -0.62
    VM
    -0.62
    eyed
    -0.61
    Pie
    -0.60
    POSITIVE LOGITS
     be
    1.06
     doubtless
    1.06
     undoubtedly
    1.00
     introduce
    0.96
     allow
    0.95
     likely
    0.94
     probably
    0.93
     revive
    0.91
     eventually
    0.91
     eliminate
    0.91
    Act Density 0.155%

    No Known Activations