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

    Neuronpedia

    INDEX
    Explanations

    words related to confidence and assurance

    oai_token-act-pair · gpt-3.5-turbo

    expressions of approval or disapproval in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Controls
    -0.74
    pleted
    -0.73
    Thousands
    -0.73
     Scores
    -0.73
     Rooms
    -0.73
    orest
    -0.71
    Prev
    -0.71
    uilding
    -0.70
     Located
    -0.69
    oother
    -0.69
    POSITIVE LOGITS
     understatement
    1.44
     rhetorical
    1.41
     irony
    1.40
     sarc
    1.24
     sarcastic
    1.23
     cynicism
    1.22
     cliché
    1.21
     euphem
    1.19
     phr
    1.17
     paraph
    1.14
    Act Density 0.661%

    No Known Activations