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

    Neuronpedia

    INDEX
    Explanations

    quotations or references

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     quoted
    -1.05
    quoted
    -0.81
     quotations
    -0.69
     Quoted
    -0.61
     quotes
    -0.56
     quotation
    -0.54
    InitVars
    -0.54
    gonic
    -0.52
     quoting
    -0.51
     Turnier
    -0.49
    POSITIVE LOGITS
    quote
    2.55
    QUOTE
    1.54
    Quote
    1.48
     Quote
    0.97
     محفوظة
    0.92
    offsetof
    0.74
    enumii
    0.71
     intptr
    0.71
    SBATCH
    0.70
    BagConstraints
    0.69
    Act Density 0.001%

    No Known Activations