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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate confirming or affirming actions or statements

    oai_token-act-pair · gpt-3.5-turbo

    language that indicates comparison or result-oriented conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.73
     encount
    -0.70
     reluct
    -0.68
     streng
    -0.66
    FTWARE
    -0.64
     tyr
    -0.64
    issance
    -0.62
    ricular
    -0.62
     afore
    -0.62
    olesc
    -0.60
    POSITIVE LOGITS
    ingly
    0.90
    ings
    0.81
     themselves
    0.77
    eth
    0.69
    ilies
    0.68
    adelphia
    0.67
    fully
    0.67
     Hitchcock
    0.64
    bits
    0.62
    ously
    0.62
    Act Density 0.592%

    No Known Activations