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

    Neuronpedia

    INDEX
    Explanations

    adjectives and descriptors that convey a sense of quality or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wise
    -0.18
    Daily
    -0.15
    917
    -0.15
    кеÑĤ
    -0.14
    itr
    -0.14
    åŁĭ
    -0.14
    ughs
    -0.14
    stitial
    -0.13
    EDIATE
    -0.13
    bil
    -0.13
    POSITIVE LOGITS
    ness
    0.43
    NESS
    0.34
    ly
    0.26
    -looking
    0.22
    nes
    0.22
     ness
    0.20
    emente
    0.20
     enough
    0.20
    ities
    0.18
    íķľ
    0.18
    Act Density 0.259%

    No Known Activations