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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific numerical values or sequences in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.86
    fficients
    -0.83
    osoba
    -0.80
    jooq
    -0.75
     विश्वसनीयता
    -0.72
    AddTagHelper
    -0.71
    aarrggbb
    -0.65
     الحره
    -0.65
    ніципалі
    -0.64
    StoryboardSegue
    -0.63
    POSITIVE LOGITS
    Obrázky
    0.60
    tri
    0.47
    amp
    0.46
    賀状
    0.44
    stahl
    0.44
    ngdoc
    0.44
    Biography
    0.43
     newBuilder
    0.43
    cur
    0.42
    Δ
    0.40
    Act Density 0.443%

    No Known Activations