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

    Neuronpedia

    INDEX
    Explanations

    terms related to thresholds in scientific or technical contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    kehrt
    -0.71
     Unwin
    -0.70
     tàu
    -0.65
    orsese
    -0.65
     compliqué
    -0.65
     transfé
    -0.65
    uppo
    -0.64
    ษัท
    -0.63
    oiseau
    -0.61
    {}
    -0.60
    POSITIVE LOGITS
    Threshold
    1.13
     Threshold
    1.13
     threshold
    1.09
    threshold
    1.08
     thresholds
    1.08
    THRESHOLD
    0.94
    thresholds
    0.93
     Marcell
    0.89
    reshold
    0.85
     Corbett
    0.83
    Act Density 0.007%

    No Known Activations