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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "previously."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    untu
    -0.15
    ihu
    -0.15
    v
    -0.15
    ê´
    -0.15
    /documentation
    -0.14
    our
    -0.14
    _TBL
    -0.14
    cken
    -0.14
     buzz
    -0.13
     preparations
    -0.13
    POSITIVE LOGITS
    /current
    0.18
    engeance
    0.15
    ër
    0.15
    noon
    0.15
    egal
    0.15
    ities
    0.14
    cab
    0.14
     سÙģ
    0.14
    odka
    0.14
    mÄĽr
    0.14
    Act Density 0.006%

    No Known Activations