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

    Neuronpedia

    INDEX
    Explanations

    instances of proper nouns or names related to people or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shakspeare
    -0.93
    bbene
    -0.89
     ſhe
    -0.86
    %"),
    -0.85
    に
    -0.85
    Grüsse
    -0.85
     Houſe
    -0.84
     faſt
    -0.84
     alſo
    -0.83
    strix
    -0.83
    POSITIVE LOGITS
    Me
    1.11
     Me
    1.05
     Se
    0.96
    Re
    0.96
    Se
    0.94
    Be
    0.93
    La
    0.92
     Re
    0.92
    Te
    0.92
    Ge
    0.91
    Act Density 0.181%

    No Known Activations