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

    Neuronpedia

    INDEX
    Explanations

    strings and identifiers used in coding or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    syntax tokens that mark structure in code or markup, like tag delimiters, field prefixes, and operator-style punctuation.

    oai_token-act-pair · gpt-5Triggered by @timna
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.93
     snippetHide
    -0.85
    oredCriteria
    -0.69
    ReusableCell
    -0.65
     dAtA
    -0.65
     betweenstory
    -0.64
     '\\;'
    -0.64
     Seeder
    -0.64
     Numerade
    -0.63
    principalTable
    -0.62
    POSITIVE LOGITS
     Wiktionnaire
    0.55
    cbs
    0.53
    ​—
    0.52
    keda
    0.50
     pés
    0.49
    0.47
    metz
    0.47
    怪
    0.47
    iella
    0.47
    0.47
    Act Density 0.081%

    No Known Activations