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

    Neuronpedia

    INDEX
    Explanations

    occurrences of backticks and code snippets within text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    avajillas
    -0.94
    σθαι
    -0.89
    •••
    -0.87
     Penh
    -0.85
     Paredes
    -0.84
     Ratna
    -0.84
    olith
    -0.82
    HttpContext
    -0.79
     rootReducer
    -0.79
     Hamm
    -0.77
    POSITIVE LOGITS
    :`
    1.52
     `
    1.51
    .`
    1.48
    {`
    1.47
    =`
    1.46
    )`
    1.37
    "`
    1.36
     (`
    1.36
    (`
    1.30
    >`
    1.26
    Act Density 0.060%

    No Known Activations