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

    Neuronpedia

    INDEX
    Explanations

    references to various types of code structures and conditions

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

    terms and identifiers related to programming and computer science concepts, particularly focusing on acronyms or technical terms frequently used in code.

    oai_token-act-pair · gpt-4oTriggered by @timna

    short, often capitalized prefix chunks within code-style identifiers and acronyms (CamelCase or ALLCAPS components).

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
    ,
    -0.68
     <<<<<<<<<<<<<<
    -0.65
     administrativos
    -0.61
     יום
    -0.60
    Compartir
    -0.57
     decidido
    -0.56
     Италијани
    -0.55
    UTERS
    -0.53
    presto
    -0.53
    numerusform
    -0.53
    POSITIVE LOGITS
    IBLIO
    0.82
    neſs
    0.78
    ſo
    0.78
    zegor
    0.76
     Diſ
    0.76
     phal
    0.72
     Conſ
    0.71
     caes
    0.71
    ghijklmnop
    0.71
     Expl
    0.71
    Act Density 0.337%

    No Known Activations