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

    Neuronpedia

    INDEX
    Explanations

    verbs tied to introverted characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to introspection and personality traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sutherland
    -0.76
     Millennium
    -0.75
     Ivory
    -0.67
     precincts
    -0.65
     Shogun
    -0.63
     Pharmaceutical
    -0.62
     Pru
    -0.61
     Vaughan
    -0.60
     Franks
    -0.60
     Laurent
    -0.59
    POSITIVE LOGITS
    spection
    1.73
    spective
    1.62
    verted
    1.52
    vert
    1.19
    spect
    1.16
    verts
    1.16
    version
    1.13
    verting
    1.00
    jection
    0.97
    itial
    0.96
    Act Density 0.021%

    No Known Activations