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

    Neuronpedia

    INDEX
    Explanations

    a diverse range of significant nouns and verbs in text that indicate complex or thematic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayar
    -0.16
    atsu
    -0.15
    berger
    -0.15
    ao
    -0.14
    Ħ
    -0.14
    rog
    -0.14
     Jr
    -0.13
    adoo
    -0.13
    pheric
    -0.13
    _IMPLEMENT
    -0.13
    POSITIVE LOGITS
    andr
    0.16
    .cmd
    0.15
    .sel
    0.15
    eta
    0.14
    CursorPosition
    0.14
    endencies
    0.14
    annis
    0.14
     Bris
    0.14
    817
    0.14
     BoxFit
    0.14
    Act Density 0.002%

    No Known Activations