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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or lack of confidence

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -1.04
     <<<<<<<<<<<<<<
    -0.98
    .*")]
    -0.97
    audiovisuel
    -0.96
     iconFacebook
    -0.91
    ^(@)
    -0.89
     iconTwitter
    -0.89
     Efq
    -0.88
    WireFormatLite
    -0.88
    mitives
    -0.87
    POSITIVE LOGITS
     sure
    0.93
     SURE
    0.89
     sur
    0.79
     Sure
    0.78
    Sure
    0.77
    sure
    0.77
    le
    0.70
    grà
    0.69
    Sura
    0.69
    sura
    0.65
    Act Density 0.016%

    No Known Activations