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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word 'detected' and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĭ
    -3.63
    ĥ½
    -3.56
    ı
    -3.10
    IJ
    -2.95
    ĨĴ
    -2.95
    į
    -2.94
    ĸ
    -2.87
    »¿
    -2.86
    ½
    -2.86
    Ĺ
    -2.83
    POSITIVE LOGITS
     gaps
    1.67
     utter
    1.52
    ently
    1.48
     him
    1.40
     bullet
    1.35
     rid
    1.34
     spot
    1.34
     intervals
    1.34
    ty
    1.33
     wing
    1.32
    Act Density 0.007%

    No Known Activations