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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases involving negation or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    823
    -0.16
    alia
    -0.16
    354
    -0.16
     Singleton
    -0.16
    ering
    -0.16
    thic
    -0.15
    omer
    -0.15
    er
    -0.15
    uada
    -0.14
    arda
    -0.14
    POSITIVE LOGITS
    infeld
    0.15
    afc
    0.15
    esModule
    0.15
    à¥Ģà¤ĸ
    0.15
    .nlm
    0.15
    exo
    0.14
    Äįem
    0.14
     Mesa
    0.14
     sóng
    0.14
    _lineno
    0.13
    Act Density 0.001%

    No Known Activations