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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ges
    -0.17
    zes
    -0.17
    ãĤ¯ãĥĪ
    -0.16
    elah
    -0.15
     hack
    -0.15
    ster
    -0.14
    iness
    -0.14
    象
    -0.14
    hack
    -0.14
    ubar
    -0.14
    POSITIVE LOGITS
     nÃło
    0.16
    logan
    0.14
    leÅŁme
    0.14
     Verde
    0.14
    /banner
    0.14
    porn
    0.14
    056
    0.13
    amerate
    0.13
    bout
    0.13
    ticker
    0.13
    Act Density 0.006%

    No Known Activations