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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quality or positive attributes of entities or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.61
     HasFactory
    -0.54
     snippetHide
    -0.53
    aturing
    -0.51
    Архівовано
    -0.49
    JsonPropertyName
    -0.49
    poptotic
    -0.48
    getAction
    -0.48
    สติ
    -0.47
     liability
    -0.47
    POSITIVE LOGITS
     Well
    1.27
    Well
    1.27
     well
    1.25
    well
    1.13
     WELL
    1.11
    WELL
    0.93
     wells
    0.79
     Wells
    0.76
     wel
    0.74
     хорошо
    0.71
    Act Density 0.106%

    No Known Activations