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

    Neuronpedia

    INDEX
    Explanations

    references to software libraries and dependencies

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     typelib
    -0.96
     itſelf
    -0.91
     myſelf
    -0.81
     againſt
    -0.77
     himſelf
    -0.76
     виправивши
    -0.75
     Jefus
    -0.73
     CreateTagHelper
    -0.73
    ValueStyle
    -0.71
    wapV
    -0.71
    POSITIVE LOGITS
    -
    0.52
     wild
    0.51
     значит
    0.48
    titur
    0.48
    olk
    0.46
     yolks
    0.45
    head
    0.45
    heads
    0.45
    vnd
    0.43
    ανα
    0.43
    Act Density 0.032%

    No Known Activations