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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äł
    -0.15
    eview
    -0.15
    roker
    -0.14
    #ac
    -0.14
    #ab
    -0.14
    imens
    -0.14
    ÎķÎł
    -0.14
    ">//
    -0.14
    kate
    -0.14
    ÐĶÐIJ
    -0.14
    POSITIVE LOGITS
     “
    0.19
     ‘
    0.17
    âĢ¦
    0.15
    âĢ¦↵
    0.15
    “
    0.14
    ”
    0.14
    Âł
    0.14
     âĢ¦↵
    0.13
     [âĢ¦]↵
    0.13
    ’
    0.13
    Act Density 0.084%

    No Known Activations