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

    Neuronpedia

    INDEX
    Explanations

    specific numbers and date formats

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values or quantities, particularly those associated with measurements or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tradem
    -0.96
    uations
    -0.86
    inates
    -0.81
    pmwiki
    -0.72
    aution
    -0.71
    kes
    -0.70
    kens
    -0.70
    abwe
    -0.68
     srf
    -0.68
    igible
    -0.67
    POSITIVE LOGITS
    87
    0.97
    88
    0.91
    66
    0.90
    77
    0.88
    61
    0.86
    50
    0.85
    37
    0.85
    01
    0.85
    55
    0.85
    41
    0.84
    Act Density 0.041%

    No Known Activations