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

    Neuronpedia

    INDEX
    Explanations

    references to closeness in physical or metaphorical distance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "close" and its variants relating to proximity or nearness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Edited
    -0.70
    æ©
    -0.70
    */(
    -0.68
    iple
    -0.66
    gow
    -0.66
     Cosponsors
    -0.66
     partName
    -0.66
    wine
    -0.65
    cu
    -0.65
     Posts
    -0.65
    POSITIVE LOGITS
     achieving
    1.07
     fruition
    1.05
     perfection
    1.03
     completion
    1.00
     extinction
    0.97
     completing
    0.93
     saturation
    0.93
     tears
    0.93
    sighted
    0.93
     realizing
    0.90
    Act Density 0.115%

    No Known Activations