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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "publish" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ook
    -0.19
    oh
    -0.15
    etical
    -0.15
    agg
    -0.14
    291
    -0.14
     Cove
    -0.14
     Dyn
    -0.14
    Ñĩили
    -0.14
    well
    -0.14
    ill
    -0.14
    POSITIVE LOGITS
    jabi
    0.16
    á»IJ
    0.16
    retch
    0.15
    hof
    0.15
    AffineTransform
    0.14
    erdem
    0.14
     frem
    0.14
    mia
    0.14
    пов
    0.14
    /store
    0.14
    Act Density 0.019%

    No Known Activations