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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "here."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urai
    -0.15
    featured
    -0.15
    oe
    -0.15
     Arn
    -0.14
    enna
    -0.14
    roe
    -0.14
    otos
    -0.14
     Beginner
    -0.14
    asco
    -0.14
    onus
    -0.14
    POSITIVE LOGITS
    abouts
    0.15
    /to
    0.15
     Mans
    0.15
    ween
    0.14
    (es
    0.14
    htable
    0.14
    ADATA
    0.14
    testdata
    0.14
     Mansion
    0.14
    uetype
    0.13
    Act Density 0.017%

    No Known Activations