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

    Neuronpedia

    INDEX
    Explanations

    phrases and words that indicate connections or continuations in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inka
    -0.16
    andro
    -0.15
     Inn
    -0.15
     glo
    -0.15
    outed
    -0.15
     Glo
    -0.15
    rek
    -0.15
    ERE
    -0.14
    ád
    -0.14
    inning
    -0.14
    POSITIVE LOGITS
    onium
    0.15
     addCriterion
    0.15
    iets
    0.14
    lid
    0.14
    subs
    0.14
    isher
    0.14
    pearance
    0.14
    ODULE
    0.14
    γÏĩ
    0.14
    cznie
    0.13
    Act Density 0.003%

    No Known Activations