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

    Neuronpedia

    INDEX
    Explanations

    details of events or projects that are in progress or being developed

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitional phrases indicating ongoing actions or developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obyl
    -0.91
    seless
    -0.81
    à¨
    -0.73
    ame
    -0.71
    galitarian
    -0.71
    BILL
    -0.70
    1981
    -0.69
    oof
    -0.68
    aq
    -0.67
    gru
    -0.67
    POSITIVE LOGITS
     hopefully
    1.16
     intends
    1.14
     expects
    1.09
     hopes
    1.08
     will
    1.01
     awaits
    0.99
     anticip
    0.97
     awaiting
    0.95
     expect
    0.92
     aims
    0.91
    Act Density 0.389%

    No Known Activations