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

    Neuronpedia

    INDEX
    Explanations

    phrases related to feelings of discomfort or surprise

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Financial
    -0.68
    Applications
    -0.68
     automobile
    -0.67
     à¨
    -0.65
    verning
    -0.64
    ourses
    -0.61
    Therefore
    -0.60
     guidance
    -0.60
    Economic
    -0.59
     policymakers
    -0.59
    POSITIVE LOGITS
    eeee
    1.03
     gotta
    0.96
    oooooooo
    0.91
    oooooooooooooooo
    0.87
     fucking
    0.87
     kinda
    0.86
     kidding
    0.85
     fuckin
    0.83
    oooo
    0.83
    ?!
    0.83
    Act Density 1.010%

    No Known Activations