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

    Neuronpedia

    INDEX
    Explanations

    references to stairs, staircases, and related spatial concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tamu
    -0.58
     fej
    -0.57
     Realm
    -0.54
    去
    -0.53
     realm
    -0.52
     punt
    -0.51
    Роз
    -0.49
    ngilizce
    -0.48
    pointer
    -0.48
    utschein
    -0.47
    POSITIVE LOGITS
     climb
    1.18
     climbs
    1.17
     climber
    1.16
     Stair
    1.13
     Climb
    1.12
     ascent
    1.11
     stairs
    1.10
     climbers
    1.09
     climbing
    1.09
     Climbing
    1.09
    Act Density 0.347%

    No Known Activations