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

    Neuronpedia

    INDEX
    Explanations

    actions involving rotation or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riend
    -0.16
     steady
    -0.16
     voks
    -0.15
    ardu
    -0.15
    apus
    -0.15
    APTER
    -0.15
    raid
    -0.14
    ppo
    -0.14
     ÄIJo
    -0.14
    presso
    -0.14
    POSITIVE LOGITS
     rotation
    0.28
     TURN
    0.28
     turn
    0.27
     rotate
    0.27
    -turn
    0.26
     Rotation
    0.26
     turns
    0.25
    turn
    0.25
     rotations
    0.25
     Rotate
    0.25
    Act Density 0.069%

    No Known Activations