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

    Neuronpedia

    INDEX
    Explanations

    specific phrases that are unrelated to common language patterns or coherent meanings

    oai_token-act-pair · gpt-3.5-turbo

    aesthetic or artistic expressions in varied contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.89
     msec
    -0.85
    nyder
    -0.78
     assemb
    -0.72
    theless
    -0.72
     McCann
    -0.67
     Riley
    -0.66
    wagen
    -0.66
    ernels
    -0.65
    abase
    -0.64
    POSITIVE LOGITS
    ¥
    1.62
    ı
    1.55
    ²
    1.53
    Į
    1.49
    ĭ
    1.47
    Ķ
    1.47
    ´
    1.46
    Ł
    1.45
    İ
    1.43
    Ī
    1.43
    Act Density 0.014%

    No Known Activations