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

    Neuronpedia

    INDEX
    Explanations

    years

    oai_token-act-pair · gpt-3.5-turbo

    references to the 16th century

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olicy
    -0.80
     tremend
    -0.79
    pmwiki
    -0.72
    atre
    -0.70
    onse
    -0.69
    rison
    -0.68
    ĺħ
    -0.67
    atem
    -0.67
    orter
    -0.66
    pherd
    -0.65
    POSITIVE LOGITS
    384
    1.32
    6666
    1.16
    th
    0.98
    05
    0.96
    09
    0.95
    07
    0.95
    03
    0.93
    06
    0.91
    08
    0.88
    02
    0.87
    Act Density 0.038%

    No Known Activations