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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and symbols in code snippets

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ellido
    -0.82
     Normdatei
    -0.69
    creativecommons
    -0.66
    erokee
    -0.65
     Schult
    -0.63
     ADN
    -0.61
    setOutput
    -0.61
     createSprite
    -0.61
    发表于
    -0.60
    ...@
    -0.60
    POSITIVE LOGITS
    ¦
    1.24
     ¦
    0.98
     Bubbles
    0.72
     Seizures
    0.71
    bbene
    0.69
     TokenType
    0.69
    bcryptjs
    0.69
     lexer
    0.69
     seizures
    0.67
     Sympathy
    0.67
    Act Density 0.000%

    No Known Activations