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

    Neuronpedia

    INDEX
    Explanations

    phrases ending with proper punctuation

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong emotional or impactful language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     withdraw
    -0.82
    ignt
    -0.75
     citiz
    -0.73
     conclude
    -0.71
    ertodd
    -0.69
    gements
    -0.69
     detract
    -0.68
     uphold
    -0.68
     dissu
    -0.67
     prosec
    -0.66
    POSITIVE LOGITS
    Consider
    0.92
    Sure
    0.89
    SHARE
    0.86
    Seriously
    0.86
    Unless
    0.85
    Published
    0.84
    Actor
    0.82
    Fans
    0.81
    DON
    0.79
    Except
    0.79
    Act Density 0.484%

    No Known Activations