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

    Neuronpedia

    INDEX
    Explanations

    instances of specific actions or directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erspective
    -0.17
    la
    -0.14
    emes
    -0.14
    _PATCH
    -0.14
     Cobb
    -0.14
     Zy
    -0.14
    aln
    -0.13
    ma
    -0.13
    uelle
    -0.13
    ripp
    -0.13
    POSITIVE LOGITS
    ạnh
    0.15
     Tah
    0.14
     Kami
    0.14
    /inet
    0.14
     blindness
    0.14
    Ãły
    0.14
    addon
    0.14
     closures
    0.14
     Inherits
    0.14
    cul
    0.13
    Act Density 0.058%

    No Known Activations