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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    IBLE
    -0.80
    taining
    -0.71
    izable
    -0.71
    BLIC
    -0.69
    ãĥ¯ãĥ³
    -0.69
    terday
    -0.68
    ׾
    -0.67
    edience
    -0.65
    tained
    -0.64
    isable
    -0.64
    POSITIVE LOGITS
    oon
    0.92
    rang
    0.90
    rance
    0.85
    staff
    0.80
    oons
    0.78
    ering
    0.75
    arts
    0.75
    lust
    0.73
    omorph
    0.72
    ames
    0.71
    Act Density 0.208%

    No Known Activations