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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "once" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    حياته
    -0.58
     HttpNotFound
    -0.57
    unnitel
    -0.55
    marvin
    -0.54
     morire
    -0.50
     uiteindelijk
    -0.50
    /**
    -0.50
     tantôt
    -0.49
    Geografi
    -0.48
    ftagPool
    -0.47
    POSITIVE LOGITS
     again
    0.96
     upon
    0.93
     Upon
    0.83
     bitten
    0.81
    upon
    0.76
     UPON
    0.76
    again
    0.75
    Upon
    0.71
    Again
    0.70
     Again
    0.67
    Act Density 0.065%

    No Known Activations