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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific names or titles

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bean
    -0.94
     Schwe
    -0.83
     GF
    -0.83
     bean
    -0.81
     Progressive
    -0.79
     Chloe
    -0.78
     bould
    -0.77
     Powell
    -0.77
     Warren
    -0.76
     Albany
    -0.76
    POSITIVE LOGITS
    ir
    2.04
    IR
    1.74
    Ir
    1.60
     IR
    1.56
    iris
    1.53
     ir
    1.46
     Ir
    1.46
    ire
    1.44
    irs
    1.39
    iri
    1.38
    Act Density 0.271%

    No Known Activations