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

    Neuronpedia

    INDEX
    Explanations

    references to characters in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <h1>
    -0.52
     Blitz
    -0.51
     {}));
    -0.50
    ⏩
    -0.50
    <bos>
    -0.49
     Abbey
    -0.47
     <=",
    -0.47
    zbęd
    -0.46
     Bisnis
    -0.46
     Eno
    -0.45
    POSITIVE LOGITS
    Character
    1.05
     Character
    1.05
     character
    1.00
    character
    0.98
     Characters
    0.96
    Characters
    0.93
     characters
    0.91
    characters
    0.91
     CHARACTER
    0.90
    CHARACTER
    0.90
    Act Density 0.051%

    No Known Activations