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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values and data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     demais
    -0.82
     Borja
    -0.78
     leaſt
    -0.78
     juſt
    -0.76
     itſelf
    -0.75
    Tembelea
    -0.75
     poffible
    -0.74
    bbene
    -0.74
     "\<
    -0.74
     blest
    -0.74
    POSITIVE LOGITS
     number
    1.65
     Number
    1.57
     NUMBER
    1.54
     numbers
    1.53
    Number
    1.47
    NUMBER
    1.41
    number
    1.40
     Numbers
    1.37
    Numbers
    1.31
    numbers
    1.30
    Act Density 0.144%

    No Known Activations