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

    Neuronpedia

    INDEX
    Explanations

    phrases related to travel and exploration

    oai_token-act-pair · gpt-3.5-turbo

    references to travel and movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uracy
    -0.68
    FORE
    -0.62
     Emer
    -0.60
     occupant
    -0.58
    moil
    -0.57
    rets
    -0.57
    Leave
    -0.57
    ukes
    -0.56
     inherit
    -0.56
    buster
    -0.56
    POSITIVE LOGITS
     corridors
    1.12
     stairs
    1.02
     treacherous
    1.01
     halls
    0.98
     distances
    0.94
     winding
    0.92
     lengths
    0.90
     streets
    0.90
     perilous
    0.87
     rooft
    0.86
    Act Density 0.301%

    No Known Activations