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

    Neuronpedia

    INDEX
    Explanations

    references to software development kits (SDKs) and related technical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific publications and software development kits (SDKs)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nea
    -0.89
    husband
    -0.85
    antha
    -0.82
    ĪĴ
    -0.80
    ctica
    -0.73
    orset
    -0.72
    omial
    -0.71
    ecause
    -0.70
    ĵĺ
    -0.70
    yright
    -0.70
    POSITIVE LOGITS
     Spiegel
    1.41
     warr
    0.84
     Schwe
    0.82
     Tanz
    0.81
     Fein
    0.80
    sburg
    0.78
    iegel
    0.77
     SPI
    0.76
     Kafka
    0.76
     Schwarz
    0.73
    Act Density 0.013%

    No Known Activations