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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erset
    -0.14
    inand
    -0.14
     Renders
    -0.14
    _opcode
    -0.14
    oÄŁlu
    -0.14
    requ
    -0.13
    ught
    -0.13
    isce
    -0.13
    Ñĩин
    -0.13
    ughters
    -0.13
    POSITIVE LOGITS
    ailer
    0.17
    aha
    0.15
    ocks
    0.14
    itom
    0.14
    itten
    0.14
    FileSystem
    0.14
    mailer
    0.14
    éª
    0.14
     Zucker
    0.14
    agher
    0.13
    Act Density 0.200%

    No Known Activations