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

    Neuronpedia

    INDEX
    Explanations

    phrases and numbers related to quantities and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cordero
    -0.62
    Rodrigo
    -0.55
    ILog
    -0.55
     Rabin
    -0.55
     Cardona
    -0.54
     Bobo
    -0.54
    Kri
    -0.54
     xiao
    -0.52
    ilak
    -0.52
     Corso
    -0.51
    POSITIVE LOGITS
    7
    1.45
    ７
    0.79
    8
    0.78
    ۷
    0.77
     seventy
    0.73
    6
    0.73
    ৭
    0.72
     zeven
    0.70
     Seventy
    0.63
     seven
    0.61
    Act Density 0.558%

    No Known Activations