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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.83
    .
    -0.64
    ,
    -0.63
     (
    -0.62
     by
    -0.60
     "
    -0.59
     “
    -0.57
     and
    -0.57
     for
    -0.56
     to
    -0.55
    POSITIVE LOGITS
     Majefty
    1.00
     كومونز
    0.94
     Efq
    0.92
    fjspx
    0.90
     Cæsar
    0.90
     purpoſe
    0.89
     doubtnut
    0.87
     queſta
    0.86
     nahilalakip
    0.84
     Reſ
    0.83
    Act Density 1.908%

    No Known Activations