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

    Neuronpedia

    INDEX
    Explanations

    tokens that represent numbers or numerical sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.22
     themſelves
    -1.20
    ftagPool
    -1.19
    -1.16
     myſelf
    -1.13
     ―――――
    -1.13
     Италијани
    -1.13
     doubtnut
    -1.13
    IndentedString
    -1.10
    Datuak
    -1.10
    POSITIVE LOGITS
    '
    0.74
     ,
    0.58
     and
    0.57
    ’
    0.57
     the
    0.57
     or
    0.55
     be
    0.54
    </h2>
    0.54
     I
    0.53
     is
    0.52
    Act Density 0.233%

    No Known Activations