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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating communication or statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yar
    -0.15
    è§
    -0.15
    ives
    -0.15
    bson
    -0.15
    greg
    -0.14
     dawn
    -0.14
    isel
    -0.14
    .gca
    -0.14
    BOSE
    -0.14
     Zoo
    -0.13
    POSITIVE LOGITS
    ored
    0.17
    ataka
    0.16
    curity
    0.16
    itung
    0.15
    onec
    0.15
    arda
    0.15
    otts
    0.15
    abase
    0.15
    ãĥįãĥ«
    0.14
    uhe
    0.14
    Act Density 0.021%

    No Known Activations