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

    Neuronpedia

    INDEX
    Explanations

    terms related to cause and effect in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paper
    -0.16
    abbo
    -0.15
     totiž
    -0.15
    ona
    -0.15
    daq
    -0.14
    вед
    -0.14
    cop
    -0.14
    ilis
    -0.14
    para
    -0.13
    iding
    -0.13
    POSITIVE LOGITS
     bee
    0.15
     p
    0.15
    _ctor
    0.15
    UFFIX
    0.14
    azo
    0.13
     fur
    0.13
    CTS
    0.13
     Phen
    0.13
     Fen
    0.13
    OF
    0.13
    Act Density 1.204%

    No Known Activations