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

    Neuronpedia

    INDEX
    Explanations

    references to comedy and political commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    brief
    -0.15
    aden
    -0.14
    datable
    -0.14
    SelectionMode
    -0.13
     Ricardo
    -0.13
    ainty
    -0.13
    ollah
    -0.13
    zá
    -0.13
    _sf
    -0.13
    scan
    -0.13
    POSITIVE LOGITS
     bi
    0.35
    .bi
    0.26
     Bi
    0.26
    bi
    0.26
    Bi
    0.24
     biography
    0.24
     historical
    0.21
     бÑĸ
    0.20
     Biography
    0.20
     би
    0.20
    Act Density 0.102%

    No Known Activations