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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific nouns, particularly related to entities, locations, and defined concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Laurent
    -0.16
    ervas
    -0.15
    ulace
    -0.15
     å±
    -0.14
    ÅĻi
    -0.14
    ourd
    -0.14
    onta
    -0.14
    ager
    -0.14
    API
    -0.14
    anvas
    -0.14
    POSITIVE LOGITS
    yles
    0.19
    SETS
    0.16
    ̣
    0.15
    anas
    0.15
    ples
    0.14
    _itr
    0.14
    .documentation
    0.14
    yth
    0.14
    µ
    0.13
    ห
    0.13
    Act Density 0.050%

    No Known Activations