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

    Neuronpedia

    INDEX
    Explanations

    various phrases that indicate action or potential development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kla
    -0.51
    __(/*!
    -0.50
    ьаж
    -0.46
    vs
    -0.46
     mustered
    -0.46
     trụ
    -0.45
    tic
    -0.44
    жи
    -0.44
     vs
    -0.44
    чак
    -0.43
    POSITIVE LOGITS
     itſelf
    0.98
    BibitemShut
    0.80
     help
    0.80
     ―――――
    0.78
     Isso
    0.76
     bring
    0.76
    bibfield
    0.74
    ArrowToggle
    0.74
     gawas
    0.73
     deſt
    0.73
    Act Density 0.723%

    No Known Activations