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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "will."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ric
    -0.16
    oise
    -0.16
    ÃŁe
    -0.14
    öh
    -0.14
    quist
    -0.14
     Worm
    -0.14
    isen
    -0.13
    504
    -0.13
    Wizard
    -0.13
     Posting
    -0.13
    POSITIVE LOGITS
     Baghd
    0.15
    athing
    0.15
    pole
    0.15
    htag
    0.14
    622
    0.14
     trimest
    0.14
    ĵ¨
    0.14
    å¢ĥ
    0.14
     Jub
    0.13
    yahoo
    0.13
    Act Density 0.053%

    No Known Activations