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

    Neuronpedia

    INDEX
    Explanations

    percentage or statistical information, especially involving numerical values and formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rase
    -0.17
    o
    -0.17
    nt
    -0.16
    ivan
    -0.15
    sted
    -0.15
    atter
    -0.15
    ÐļТ
    -0.14
    enal
    -0.14
    (gca
    -0.14
    lo
    -0.14
    POSITIVE LOGITS
    DataStream
    0.22
    achen
    0.15
    Violation
    0.15
    νή
    0.14
    relay
    0.14
    elen
    0.14
    rouch
    0.14
    ľ
    0.14
    thenReturn
    0.13
    ijo
    0.13
    Act Density 0.004%

    No Known Activations