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

    Neuronpedia

    INDEX
    Explanations

    printed words or text related to products or designs

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to items or components in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Recomm
    -0.67
    needs
    -0.65
    Unknown
    -0.65
    Was
    -0.63
     starved
    -0.63
    lier
    -0.63
    Angelo
    -0.63
    flying
    -0.62
     waning
    -0.61
     Says
    -0.61
    POSITIVE LOGITS
     consist
    1.38
     contain
    1.38
     differ
    1.34
     comprise
    1.33
     are
    1.29
     allow
    1.28
     depict
    1.25
     vary
    1.25
     provide
    1.24
     encompass
    1.23
    Act Density 0.246%

    No Known Activations