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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "on."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Versch
    -0.73
     angele
    -0.72
    CCCC
    -0.71
    docx
    -0.64
     attentions
    -0.62
    theta
    -0.60
    HART
    -0.60
    ladı
    -0.60
    Eph
    -0.60
    ocus
    -0.59
    POSITIVE LOGITS
    ukseen
    0.70
     reaſon
    0.68
    CDN
    0.68
     Huron
    0.67
     Vicksburg
    0.66
     Speer
    0.66
    ed
    0.65
    otyp
    0.65
    berday
    0.64
     fhew
    0.64
    Act Density 0.014%

    No Known Activations