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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names related to individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Forums
    -0.18
     naked
    -0.17
    atcher
    -0.15
    éľ²
    -0.15
    agara
    -0.14
     Naked
    -0.14
    dra
    -0.14
     forums
    -0.14
    ObjectContext
    -0.14
     Lafayette
    -0.13
    POSITIVE LOGITS
     вел
    0.17
    æı¡
    0.15
    çĮ
    0.15
    rew
    0.15
    ushman
    0.14
    GuidId
    0.14
    eyin
    0.14
     Evet
    0.14
    _vlog
    0.14
     Jam
    0.14
    Act Density 0.299%

    No Known Activations