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

    Neuronpedia

    INDEX
    Explanations

    mentions of numerical quantities and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ennie
    -0.17
    zung
    -0.16
    adele
    -0.15
    eters
    -0.15
    ><![
    -0.15
    anje
    -0.14
    orro
    -0.14
    ixo
    -0.14
    uxtap
    -0.14
    olina
    -0.14
    POSITIVE LOGITS
     numbers
    0.44
    numbers
    0.38
     number
    0.36
     Numbers
    0.34
    Numbers
    0.32
     count
    0.31
    number
    0.31
    _numbers
    0.30
    æķ°éĩı
    0.30
    -num
    0.30
    Act Density 0.172%

    No Known Activations