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

    Neuronpedia

    INDEX
    Explanations

    occurrences of function definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amber
    -0.18
    ilmington
    -0.14
     meille
    -0.14
    ç±
    -0.14
    ozilla
    -0.14
    inka
    -0.14
    OGLE
    -0.13
    frey
    -0.13
    arkan
    -0.13
    otta
    -0.13
    POSITIVE LOGITS
    ering
    0.18
    oton
    0.16
     Acid
    0.15
    tern
    0.15
    acid
    0.15
    ern
    0.15
     acid
    0.15
    .scalablytyped
    0.14
    igr
    0.14
     quot
    0.14
    Act Density 0.098%

    No Known Activations