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

    Neuronpedia

    INDEX
    Explanations

    descriptors that emphasize beauty and aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wise
    -0.18
    yles
    -0.17
    ella
    -0.15
    erty
    -0.15
     measures
    -0.15
     greatness
    -0.15
    ette
    -0.15
    yle
    -0.14
    contract
    -0.14
    å¾
    -0.13
    POSITIVE LOGITS
    lest
    0.23
    mente
    0.16
    emente
    0.16
    _AUX
    0.15
    ippets
    0.15
     GetLastError
    0.15
     *__
    0.15
    (er
    0.15
    gom
    0.15
    awns
    0.15
    Act Density 0.072%

    No Known Activations