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

    Neuronpedia

    INDEX
    Explanations

    references to figures in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     derer
    -0.72
    __________
    -0.71
     ་་
    -0.70
    #>
    -0.69
     itſelf
    -0.67
    #{
    -0.67
     rime
    -0.66
     */;
    -0.66
    ᵉ
    -0.66
     Houſe
    -0.65
    POSITIVE LOGITS
     Fig
    3.28
    Fig
    3.18
     Figs
    2.45
    Figs
    2.29
     fig
    2.12
    fig
    1.95
     FIG
    1.81
     figs
    1.67
    FIG
    1.60
     Sept
    1.27
    Act Density 0.152%

    No Known Activations