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

    Neuronpedia

    INDEX
    Explanations

    specific references or mentions in a text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word 'reference' and its context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awk
    -0.81
    keye
    -0.80
    Ģ
    -0.78
    ilon
    -0.76
    ihad
    -0.76
    alach
    -0.73
    ouk
    -0.69
    cffff
    -0.69
    ¯¯¯¯
    -0.69
    oeuv
    -0.67
    POSITIVE LOGITS
     references
    0.86
    reference
    0.78
     Reference
    0.77
    ibly
    0.72
    ="#
    0.72
     reference
    0.71
    minist
    0.68
    ibility
    0.68
    ogue
    0.66
    PsyNetMessage
    0.66
    Act Density 0.017%

    No Known Activations