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

    Neuronpedia

    INDEX
    Explanations

    segments labeled as "Part" in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erator
    -0.20
    aths
    -0.17
    pline
    -0.17
    pane
    -0.16
    eliness
    -0.15
    ated
    -0.14
    erate
    -0.14
    athing
    -0.14
    ward
    -0.14
     parte
    -0.14
    POSITIVE LOGITS
    icular
    0.35
    icip
    0.33
    ly
    0.33
    icipation
    0.32
    ners
    0.30
    isan
    0.30
    ially
    0.26
    icularly
    0.26
    ies
    0.23
     partition
    0.23
    Act Density 0.021%

    No Known Activations