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

    Neuronpedia

    INDEX
    Explanations

    detailed information on diverse topics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ruary
    -0.62
    asus
    -0.59
    ushima
    -0.57
    bda
    -0.56
    unts
    -0.55
    UNCH
    -0.55
    ÅŁ
    -0.54
    ffee
    -0.54
    steen
    -0.54
    asper
    -0.53
    POSITIVE LOGITS
    worldly
    1.17
    wise
    0.90
    itarian
    0.87
    ities
    0.70
    soever
    0.62
    kin
    0.61
    swer
    0.61
    yne
    0.60
     Languages
    0.60
    mis
    0.59
    Act Density 0.492%

    No Known Activations