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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating specific locations or physical placements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uko
    -0.56
     Sense
    -0.56
    ARA
    -0.55
    rollers
    -0.55
     asses
    -0.54
     Anything
    -0.54
    icipated
    -0.53
    ESE
    -0.53
     Flavoring
    -0.53
     diapers
    -0.53
    POSITIVE LOGITS
     smack
    1.09
     atop
    1.08
     northwest
    1.00
     near
    0.99
     northeast
    0.99
     beside
    0.98
     southwest
    0.98
     adjacent
    0.94
     southeast
    0.93
     halfway
    0.93
    Act Density 0.081%

    No Known Activations