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

    Neuronpedia

    INDEX
    Explanations

    code snippets or formatting cues related to indentation or line breaks

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     Bra
    -0.63
    Bra
    -0.57
     http
    -0.55
    http
    -0.54
     pinulongan
    -0.54
    y
    -0.54
    2
    -0.54
    `
    -0.52
     Bro
    -0.52
    1
    -0.52
    POSITIVE LOGITS
    br
    1.03
    CloseOperation
    0.91
    ConstraintMaker
    0.88
     br
    0.79
    :✨
    0.78
     '\\;'
    0.78
    NUMX
    0.71
     Gregorian
    0.71
     öffnungszeiten
    0.70
    ^(@)
    0.70
    Act Density 0.001%

    No Known Activations