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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specificity and particularity in the discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivol
    -0.15
    ional
    -0.15
    IENTATION
    -0.15
    .trace
    -0.14
    icopt
    -0.14
    _PIX
    -0.14
    meg
    -0.14
    phem
    -0.14
    OKIE
    -0.14
    Meg
    -0.14
    POSITIVE LOGITS
    аÑĤÑĭ
    0.15
    jen
    0.14
     Baths
    0.14
     Albert
    0.14
     Bart
    0.14
     Weber
    0.14
    à¤Ŀ
    0.13
     zeroes
    0.13
     Exhaust
    0.13
    tons
    0.13
    Act Density 0.047%

    No Known Activations