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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical operations or concepts related to rounding and flooring values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    saraba
    -0.67
    ficulty
    -0.55
     råd
    -0.54
    ály
    -0.53
    felder
    -0.52
    abestanden
    -0.52
    μέ
    -0.51
    
    -0.50
    έρα
    -0.50
    ņem
    -0.49
    POSITIVE LOGITS
     ceil
    0.93
    ceil
    0.91
    floor
    0.80
    round
    0.76
    UnitTesting
    0.73
    rceil
    0.72
     Majefty
    0.71
     HasFactory
    0.70
     Basse
    0.70
     Floor
    0.69
    Act Density 0.071%

    No Known Activations