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

    Neuronpedia

    INDEX
    Explanations

    instances of comparison or contrasting elements within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     batt
    -0.16
    (IService
    -0.15
    bury
    -0.15
    heimer
    -0.15
     Alto
    -0.15
    eph
    -0.14
    gone
    -0.14
     Guth
    -0.14
    innie
    -0.14
    .daily
    -0.14
    POSITIVE LOGITS
     exceptions
    0.18
    Remaining
    0.17
    exceptions
    0.17
     Exceptions
    0.17
     समर
    0.15
    Exceptions
    0.15
     exemple
    0.15
    ãĤĤãģĨ
    0.15
     Ih
    0.15
     주ìļĶ
    0.15
    Act Density 0.045%

    No Known Activations