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
    Collegamenti
    -0.90
     iconFacebook
    -0.90
    ArrowToggle
    -0.86
     BoxDecoration
    -0.85
     Edith
    -0.85
     <<<<<<<<<<<<<<
    -0.82
     abe
    -0.79
     Obrador
    -0.79
    helf
    -0.79
    mitives
    -0.79
    POSITIVE LOGITS
     SURE
    1.22
     sure
    1.16
     Sure
    1.02
    Sure
    1.00
    sure
    0.99
     sur
    0.79
     sureties
    0.73
     Sura
    0.72
     sûre
    0.72
     Uncertain
    0.71
    Act Density 0.044%

    No Known Activations