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

    Neuronpedia

    INDEX
    Explanations

    classes and methods in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pey
    -0.16
    abyrinth
    -0.16
    isy
    -0.15
     Caul
    -0.14
    ebb
    -0.14
    chip
    -0.14
    aro
    -0.14
     Peb
    -0.14
    xygen
    -0.13
    GRAM
    -0.13
    POSITIVE LOGITS
    iral
    0.20
    lord
    0.20
    ilde
    0.18
    lor
    0.18
    urch
    0.17
    alleng
    0.16
    APTER
    0.16
    imer
    0.16
    amber
    0.16
    allenges
    0.16
    Act Density 0.037%

    No Known Activations