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

    Neuronpedia

    INDEX
    Explanations

    the word "once" and its variations, indicating repetitions or conditions of occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.68
     understatement
    -0.61
    saraba
    -0.61
    maline
    -0.59
    lastic
    -0.57
    kungen
    -0.57
    pacho
    -0.55
    ლი
    -0.54
     gradova
    -0.53
    membrance
    -0.53
    POSITIVE LOGITS
    Once
    1.84
     Once
    1.83
     once
    1.65
     ONCE
    1.57
    once
    1.55
    ONCE
    1.54
     Sobald
    1.02
     einmal
    0.95
     sobald
    0.87
     vez
    0.83
    Act Density 0.205%

    No Known Activations