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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or incredulity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     चीज़ों
    -0.59
    kloped
    -0.58
    };*/
    -0.56
    PositiveButton
    -0.54
    __":
    -0.54
    ftagPool
    -0.54
    SBATCH
    -0.54
    getMenuInflater
    -0.53
    ---*/
    -0.53
    uxxxx
    -0.53
    POSITIVE LOGITS
     Beware
    0.78
     beware
    0.72
     WTF
    0.69
    BTW
    0.68
    Yay
    0.66
    harusnya
    0.65
     BTW
    0.65
     montes
    0.65
     оригіналу
    0.64
     ghi
    0.64
    Act Density 0.248%

    No Known Activations