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

    Neuronpedia

    INDEX
    Explanations

    superlatives or comparisons, specifically regarding physical proximity or similarity

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    mA
    -1.15
    iasis
    -1.12
    士
    -1.09
    AIN
    -1.01
    EED
    -1.01
    anity
    -0.97
    Percent
    -0.96
    rone
    -0.96
    ONES
    -0.96
    DOM
    -0.95
    POSITIVE LOGITS
     thereto
    1.28
    sighted
    1.20
     proximity
    1.20
     confid
    1.19
     scrutiny
    1.17
     resemblance
    1.13
     closer
    1.01
     confinement
    1.01
     intimacy
    0.98
     analogue
    0.95
    Act Density 0.346%

    No Known Activations