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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-description or self-reliance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to self-referential or self-descriptive concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OUGH
    -0.72
     Flavoring
    -0.69
    oux
    -0.68
    iage
    -0.68
     Styles
    -0.66
     "$:/
    -0.66
     Velocity
    -0.64
     Ribbon
    -0.64
     Weeks
    -0.64
     EntityItem
    -0.62
    POSITIVE LOGITS
    proclaimed
    1.27
    contained
    1.26
    destruct
    1.14
    imposed
    1.12
    described
    1.09
    driving
    1.09
    decl
    1.08
    appointed
    1.06
    funded
    1.06
    sty
    1.03
    Act Density 0.028%

    No Known Activations