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

    Neuronpedia

    INDEX
    Explanations

    LaTeX-formatted mathematical expressions and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fjspx
    -0.98
     AssemblyCulture
    -0.91
     typelib
    -0.90
     >=",
    -0.89
    '));
    -0.86
     Roskov
    -0.85
     '\\;'
    -0.84
     <",
    -0.84
    LookAnd
    -0.83
    kháu
    -0.83
    POSITIVE LOGITS
    {
    0.55
    '
    0.54
    textit
    0.53
    mathrm
    0.51
    ization
    0.51
    ’
    0.51
    mb
    0.50
    he
    0.50
    makeText
    0.48
    ‘
    0.48
    Act Density 0.325%

    No Known Activations