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

    Neuronpedia

    INDEX
    Explanations

    instances of repeated phrases or structural patterns within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hpp
    -0.17
    readcrumbs
    -0.14
    issen
    -0.14
    ewater
    -0.14
    Bookmark
    -0.14
    ester
    -0.14
    orm
    -0.13
    vise
    -0.13
    visa
    -0.13
    quirrel
    -0.13
    POSITIVE LOGITS
     member
    0.17
    agh
    0.14
     spol
    0.14
    ustin
    0.14
    winner
    0.14
    (member
    0.14
    008
    0.13
    stal
    0.13
    boro
    0.13
    anch
    0.13
    Act Density 0.037%

    No Known Activations