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

    Neuronpedia

    INDEX
    Explanations

    the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bage
    -0.18
    fighter
    -0.16
    istor
    -0.14
    identification
    -0.14
    jack
    -0.14
    eya
    -0.14
    âk
    -0.14
     identification
    -0.13
     regards
    -0.13
    ched
    -0.13
    POSITIVE LOGITS
    yx
    0.23
    este
    0.19
    ymous
    0.19
    look
    0.18
    liner
    0.18
    gin
    0.18
    coming
    0.18
    ederland
    0.17
    us
    0.17
    omat
    0.17
    Act Density 0.056%

    No Known Activations