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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or evaluation in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ìŀ¡
    -0.15
    ConverterFactory
    -0.15
    \model
    -0.13
    ĥ
    -0.13
    RSS
    -0.12
    amp
    -0.12
     RSS
    -0.12
     predators
    -0.12
     Pru
    -0.12
     volunte
    -0.12
    POSITIVE LOGITS
    fgang
    0.16
    ibaba
    0.15
    eczy
    0.15
    asta
    0.15
    ohana
    0.14
    Specifier
    0.14
    duk
    0.14
     Už
    0.14
    tra
    0.14
    avin
    0.14
    Act Density 0.322%

    No Known Activations