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

    Neuronpedia

    INDEX
    Explanations

    code with many special characters

    oai_token-act-pair · gemini-2.0-flash

    archaic or unusual words

    np_token-act-pair-logits · gpt-4o-mini

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    </b>
    -0.67
    <b>
    -0.66
    â
    -0.66
    </i>
    -0.63
    ­
    -0.58
     &
    -0.58
    <strong>
    -0.57
    �
    -0.56
    (
    -0.56
    1
    -0.56
    POSITIVE LOGITS
     Majefty
    1.01
     Houſe
    0.94
     Jefus
    0.90
     Efq
    0.89
     Shakspeare
    0.85
    ^(@)
    0.85
     myſelf
    0.84
     becauſe
    0.82
     leaſt
    0.82
     itſelf
    0.82
    Act Density 12.785%

    No Known Activations