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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 't' and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    linger
    -0.18
    æ³Ĭ
    -0.17
    adius
    -0.16
    importe
    -0.16
    bias
    -0.15
    atik
    -0.15
    lier
    -0.14
     Ste
    -0.14
     vá»ĭ
    -0.14
    adratic
    -0.14
    POSITIVE LOGITS
    ids
    0.19
    ills
    0.19
    alet
    0.19
    ys
    0.19
    eg
    0.18
    etta
    0.18
    rosse
    0.17
     Hills
    0.17
    id
    0.17
    ona
    0.17
    Act Density 0.013%

    No Known Activations