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

    Neuronpedia

    INDEX
    Explanations

    references or citations in text

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of citing sources or evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orld
    -0.81
    ipeg
    -0.74
    ¯¯¯¯¯¯¯¯
    -0.74
    xy
    -0.71
    hattan
    -0.69
    ibaba
    -0.68
    visors
    -0.67
    ascript
    -0.67
    amination
    -0.66
    ixtape
    -0.66
    POSITIVE LOGITS
     citations
    0.95
     citation
    0.87
    enza
    0.81
     cite
    0.78
     cited
    0.76
     citing
    0.75
    âĨij
    0.70
     warnings
    0.70
     Cit
    0.70
     Forbidden
    0.70
    Act Density 0.019%

    No Known Activations