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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and letters typically associated with references or citations in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingleton
    -0.17
    abal
    -0.16
    bal
    -0.15
    iag
    -0.15
    DEX
    -0.14
    BASH
    -0.14
    REC
    -0.14
    æk
    -0.14
    iales
    -0.14
     Bald
    -0.14
    POSITIVE LOGITS
     semiclass
    0.16
    .Abstract
    0.16
    ROLS
    0.14
    _TCP
    0.14
    inet
    0.14
    æ¾
    0.14
    UTERS
    0.14
    olls
    0.14
    owell
    0.13
    getColumn
    0.13
    Act Density 0.013%

    No Known Activations