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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating types of categories or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elli
    -0.14
    330
    -0.14
    ieber
    -0.14
     Timber
    -0.14
    tim
    -0.13
    iber
    -0.13
    unger
    -0.13
     both
    -0.12
    pur
    -0.12
    gens
    -0.12
    POSITIVE LOGITS
    rome
    0.15
    xec
    0.14
    ÃŃž
    0.14
    ichert
    0.14
     müc
    0.14
    Enemies
    0.13
     Provid
    0.13
    coverage
    0.12
    TION
    0.12
    Writes
    0.12
    Act Density 0.070%

    No Known Activations