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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate navigation and directional guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    جÙĦ
    -0.15
    ountains
    -0.14
     Idle
    -0.13
    kers
    -0.13
    Gateway
    -0.13
     waterfall
    -0.13
    寿
    -0.13
    ëĭ´
    -0.13
     Ñģвид
    -0.13
    ZONE
    -0.13
    POSITIVE LOGITS
     navigation
    0.46
     directions
    0.46
     Navigation
    0.43
     direction
    0.42
     navig
    0.42
    direction
    0.38
     Directions
    0.38
     Direction
    0.36
    navigation
    0.36
    orientation
    0.35
    Act Density 0.033%

    No Known Activations