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

    Neuronpedia

    INDEX
    Explanations

    references to special or notable individuals and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eya
    -0.15
    /Sub
    -0.14
     subconscious
    -0.13
    tera
    -0.13
     Slut
    -0.13
    ensch
    -0.13
    asser
    -0.13
    ÑĤаб
    -0.13
    ugo
    -0.13
    StackSize
    -0.13
    POSITIVE LOGITS
     special
    0.90
    special
    0.82
     Special
    0.80
    Special
    0.75
     spec
    0.74
     SPECIAL
    0.73
    -special
    0.71
    pecial
    0.70
    _special
    0.69
     Spec
    0.65
    Act Density 0.287%

    No Known Activations