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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional states or evaluations of behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iloc
    -0.18
    educt
    -0.16
    ozem
    -0.16
    fillType
    -0.14
    .infinity
    -0.14
    ritz
    -0.14
    igua
    -0.14
    omor
    -0.14
    .synthetic
    -0.14
    éné
    -0.14
    POSITIVE LOGITS
    ubl
    0.16
    rosse
    0.16
    954
    0.15
    g
    0.14
     nothing
    0.14
     otherwise
    0.13
    ote
    0.13
     campaigning
    0.13
    äll
    0.13
    adi
    0.13
    Act Density 0.326%

    No Known Activations