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

    Neuronpedia

    INDEX
    Explanations

    expressions of certainty or assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -1.05
     Obrador
    -0.90
    helf
    -0.84
     autorytatywna
    -0.83
     BoxDecoration
    -0.83
    Portály
    -0.82
     Fielding
    -0.82
     Polyp
    -0.80
     iconFacebook
    -0.80
     Mackay
    -0.79
    POSITIVE LOGITS
     sure
    1.04
     SURE
    1.03
     Sure
    0.90
    Sure
    0.82
    sure
    0.78
     enough
    0.72
     Stras
    0.71
    er
    0.69
    enough
    0.67
    ure
    0.65
    Act Density 0.056%

    No Known Activations