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

    Neuronpedia

    INDEX
    Explanations

    specific sections or references within texts, particularly in academic or formal documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Des
    -0.49
    bes
    -0.48
    vs
    -0.45
    넷
    -0.45
    ↵↵
    -0.44
     Peter
    -0.44
     main
    -0.43
    lets
    -0.43
    UNRELATED
    -0.42
     des
    -0.42
    POSITIVE LOGITS
     tartalomajánló
    1.01
    esterday
    0.77
    AndEndTag
    0.76
    principalTable
    0.73
    kháu
    0.72
     Efq
    0.72
     Normdatei
    0.70
    didSet
    0.69
    AlterField
    0.68
    principalColumn
    0.68
    Act Density 0.148%

    No Known Activations