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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating actions or involvement in situations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ASIC
    -0.17
     neutr
    -0.15
    agram
    -0.15
    обов
    -0.15
    imals
    -0.15
    _cli
    -0.15
    tas
    -0.15
    erie
    -0.15
    URRED
    -0.14
    nop
    -0.14
    POSITIVE LOGITS
     fan
    0.14
    人åı£
    0.14
     Amb
    0.14
    sted
    0.14
    è´
    0.13
     ano
    0.13
     Rol
    0.13
    amble
    0.13
    ipy
    0.13
    unately
    0.13
    Act Density 0.001%

    No Known Activations