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

    Neuronpedia

    INDEX
    Explanations

    locations or places described in text

    oai_token-act-pair · gpt-3.5-turbo

    locations of intersections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apons
    -0.77
    sonian
    -0.75
    warm
    -0.74
    oult
    -0.74
    wagen
    -0.71
    zn
    -0.66
    BIT
    -0.64
    -----------
    -0.64
    zech
    -0.63
    pter
    -0.63
    POSITIVE LOGITS
     intersection
    0.87
     intersections
    0.81
     Sakuya
    0.77
    cross
    0.72
    aminer
    0.72
    lane
    0.71
     junction
    0.71
    course
    0.70
     mund
    0.68
    ues
    0.68
    Act Density 0.030%

    No Known Activations