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

    Neuronpedia

    INDEX
    Explanations

    descriptions of locations and directional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ضÙĦ
    -0.15
     corridors
    -0.15
    chant
    -0.14
     envelopes
    -0.14
     ном
    -0.14
    keit
    -0.13
     Channels
    -0.13
     voyage
    -0.13
    .Builder
    -0.13
    Backing
    -0.13
    POSITIVE LOGITS
     intersection
    0.37
     junction
    0.36
     exit
    0.34
    intersection
    0.31
     Intersection
    0.31
     intersections
    0.29
    junction
    0.28
     crossing
    0.28
     bend
    0.26
     entrance
    0.26
    Act Density 0.183%

    No Known Activations