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

    Neuronpedia

    INDEX
    Explanations

    code-related constructs or syntax elements, particularly in programming

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

    large blocks of code with multiple lines of parameters or arguments spanning across many tokens.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     enfans
    -0.36
     réunions
    -0.33
     Construcción
    -0.32
     misión
    -0.32
     leçons
    -0.31
     Könige
    -0.31
     prefeito
    -0.31
     presidenta
    -0.30
     tendances
    -0.30
     ministres
    -0.30
    POSITIVE LOGITS
    MigrationBuilder
    0.75
    findpost
    0.66
     Italijanski
    0.64
    0.60
     kasarigan
    0.59
     SDLK
    0.57
    :✨
    0.57
    ſt
    0.56
    CloseOperation
    0.56
    monial
    0.56
    Act Density 0.426%

    No Known Activations