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

    Neuronpedia

    INDEX
    Explanations

    instances of the variable "s" used in mathematical expressions or equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Rossi
    -0.77
    y
    -0.76
    Ros
    -0.74
     Pes
    -0.71
     CIS
    -0.71
     Ros
    -0.69
     Moseley
    -0.69
    mos
    -0.68
     Hayes
    -0.67
    Rujukan
    -0.67
    POSITIVE LOGITS
    theless
    0.81
     transférez
    0.79
     AssemblyCulture
    0.78
    帖最后由
    0.73
    الحياه
    0.73
    Personensuche
    0.73
    cadilly
    0.72
    檚
    0.72
    ///</
    0.71
     Impala
    0.71
    Act Density 0.089%

    No Known Activations