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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    e
    -0.27
    tone
    -0.25
    ei
    -0.24
    eing
    -0.22
    een
    -0.21
    ë¡ľ
    -0.21
    es
    -0.20
    ton
    -0.19
    o
    -0.18
    ty
    -0.18
    POSITIVE LOGITS
    ymous
    0.28
    imbus
    0.28
    nection
    0.27
    uevo
    0.27
    ics
    0.25
    ucle
    0.25
    ese
    0.24
    ned
    0.24
    etwork
    0.23
    avigation
    0.23
    Act Density 0.184%

    No Known Activations