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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical pathways or routes

    oai_token-act-pair · gpt-3.5-turbo

    references to corridors or passageways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iak
    -0.83
    itude
    -0.79
    odium
    -0.76
    enthal
    -0.74
    oras
    -0.73
    arov
    -0.70
    ullivan
    -0.68
    olute
    -0.68
    onom
    -0.67
    aina
    -0.67
    POSITIVE LOGITS
     corridors
    1.08
    ridor
    1.03
     Corridor
    0.98
     corridor
    0.98
    ttes
    0.87
     passages
    0.82
     routes
    0.79
     divid
    0.77
    ways
    0.77
     pathways
    0.73
    Act Density 0.020%

    No Known Activations