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

    Neuronpedia

    INDEX
    Explanations

    technical components or parts mentioned in sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to various components and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kers
    -0.82
    standing
    -0.79
    fm
    -0.75
    ker
    -0.72
    stretched
    -0.71
    bies
    -0.66
    ipeg
    -0.66
    hur
    -0.66
     Predators
    -0.65
    tale
    -0.65
    POSITIVE LOGITS
     components
    0.93
     parts
    0.88
     component
    0.85
     subsystem
    0.84
     thereof
    0.82
     Components
    0.80
    iation
    0.79
    onents
    0.79
     additive
    0.75
    ivity
    0.73
    Act Density 0.025%

    No Known Activations