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

    Neuronpedia

    INDEX
    Explanations

    numeric values that can be compared

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISSION
    -0.72
    lav
    -0.64
    soft
    -0.62
    ritic
    -0.58
    plin
    -0.58
    lash
    -0.57
    isoft
    -0.56
     "\
    -0.56
    actionDate
    -0.56
    potion
    -0.55
    POSITIVE LOGITS
    ocating
    0.94
    ogene
    0.83
     kinds
    0.81
    igators
    0.77
    igator
    0.77
    udes
    0.77
     sorts
    0.70
    otin
    0.70
    اØ
    0.69
    uding
    0.68
    Act Density 0.036%

    No Known Activations