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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hof
    -0.87
    atis
    -0.82
    oris
    -0.78
    selage
    -0.75
    ĸļ
    -0.71
    onom
    -0.71
    endor
    -0.70
    nih
    -0.70
    uments
    -0.70
    urion
    -0.69
    POSITIVE LOGITS
    dating
    1.00
    stairs
    0.88
    izoph
    0.87
    ban
    0.87
    coming
    0.80
    bably
    0.78
    dates
    0.78
    lishes
    0.77
    mit
    0.77
    ward
    0.76
    Act Density 0.008%

    No Known Activations