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

    Neuronpedia

    INDEX
    Explanations

    pairs of words related to spatial direction

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, specifically the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aughs
    -0.74
    manship
    -0.71
    conom
    -0.70
     Devi
    -0.70
    Rocket
    -0.67
     Logged
    -0.67
    NI
    -0.67
    Beer
    -0.66
    udence
    -0.66
     Matters
    -0.65
    POSITIVE LOGITS
     periphery
    1.16
     bottom
    1.11
     upper
    1.00
     middle
    0.98
     aft
    0.97
     foremost
    0.96
     outs
    0.94
     midrange
    0.91
     underside
    0.90
     rear
    0.90
    Act Density 0.199%

    No Known Activations