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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "once" and related conditional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Scroller
    -0.47
    ánicas
    -0.46
    oft
    -0.45
    Retry
    -0.44
     gradova
    -0.44
    ättä
    -0.41
    टक
    -0.40
    ↵
    -0.40
    NewGuid
    -0.39
    :
    -0.39
    POSITIVE LOGITS
    Datuak
    1.16
     nahilalakip
    0.92
    EndInit
    0.89
    "],
    0.86
    MethodManager
    0.86
    "),
    0.83
    ,:),
    0.83
    Portail
    0.83
    ]='\
    0.83
    NUMX
    0.81
    Act Density 0.118%

    No Known Activations