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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĬŁ
    -0.15
     Booth
    -0.15
    starter
    -0.14
     exemplary
    -0.13
    egral
    -0.13
    ::
    -0.13
    esty
    -0.13
    äºĭåĭĻ
    -0.13
     something
    -0.13
    odd
    -0.13
    POSITIVE LOGITS
    ermann
    0.15
    ayah
    0.14
    uke
    0.14
     Shuffle
    0.14
    okino
    0.13
    grily
    0.13
    etim
    0.13
     жовÑĤ
    0.13
    ukes
    0.13
    andles
    0.13
    Act Density 0.391%

    No Known Activations