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

    Neuronpedia

    INDEX
    Explanations

    themes related to writing and book completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ackson
    -0.14
     (
    -0.14
     Maj
    -0.14
    ieri
    -0.14
     shortly
    -0.14
     venue
    -0.14
     hierarchy
    -0.13
    atif
    -0.13
    asted
    -0.13
    aq
    -0.13
    POSITIVE LOGITS
     challenge
    0.43
     Challenge
    0.40
    challenge
    0.36
    Challenge
    0.35
     challenged
    0.32
    _challenge
    0.31
     challenges
    0.31
     challeng
    0.30
     Challenges
    0.29
    allenge
    0.28
    Act Density 0.090%

    No Known Activations