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

    Neuronpedia

    INDEX
    Explanations

    phrases related to walking along streets or roads

    oai_token-act-pair · gpt-3.5-turbo

    instances of walking or related motion in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLASSIFIED
    -0.75
    cial
    -0.71
    etheless
    -0.71
    Refer
    -0.69
    ibur
    -0.69
    achev
    -0.68
    leeve
    -0.67
    udder
    -0.65
    ilon
    -0.64
    rss
    -0.63
    POSITIVE LOGITS
     streets
    1.24
     corridors
    1.05
     intersections
    1.04
     sidewalks
    1.02
     downtown
    1.00
     sidewalk
    0.96
     halls
    0.96
     malls
    0.95
     darkened
    0.94
     street
    0.93
    Act Density 0.165%

    No Known Activations