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

    Neuronpedia

    INDEX
    Explanations

    instances of irony and unexpected outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gia
    -0.16
    iani
    -0.15
     WI
    -0.15
    UDGE
    -0.15
    ront
    -0.15
    _normalize
    -0.15
     FileNotFoundError
    -0.14
    à¥ĭश
    -0.14
     putchar
    -0.14
    -anchor
    -0.14
    POSITIVE LOGITS
     coincidence
    0.32
     luck
    0.32
    Luck
    0.29
     Coin
    0.28
     coinc
    0.28
     timing
    0.28
     Luck
    0.27
     Timing
    0.27
    Timing
    0.25
    Coin
    0.25
    Act Density 0.163%

    No Known Activations