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

    Neuronpedia

    INDEX
    Explanations

    instances of personal opinions and subjective assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alphabet
    -0.18
     alphabet
    -0.16
    alf
    -0.14
     themes
    -0.14
    ymbols
    -0.14
    uhe
    -0.14
     vocabulary
    -0.14
    åIJįåīį
    -0.14
     primal
    -0.13
    å°ĭ
    -0.13
    POSITIVE LOGITS
     usage
    0.23
     Usage
    0.22
    Usage
    0.21
    usage
    0.20
     USAGE
    0.19
    USAGE
    0.18
     ÑĥпоÑĤÑĢеб
    0.17
     sentence
    0.17
     English
    0.16
    zcze
    0.16
    Act Density 0.055%

    No Known Activations