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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "sure" and its variants, indicating a focus on expressions of certainty or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iconFacebook
    -0.77
    Collegamenti
    -0.76
     Schi
    -0.70
     Pollock
    -0.70
     Distrikt
    -0.69
    jména
    -0.69
     Fielding
    -0.68
    enoord
    -0.68
    TintMode
    -0.68
     Stephens
    -0.66
    POSITIVE LOGITS
    Sure
    1.74
     sure
    1.71
     Sure
    1.70
     SURE
    1.65
    sure
    1.52
     surely
    0.91
     sûr
    0.85
     Surely
    0.83
     shur
    0.78
     sûre
    0.77
    Act Density 0.045%

    No Known Activations