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

    Neuronpedia

    INDEX
    Explanations

    words related to spinning or turning around an axis

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rotation and orientation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.78
    omething
    -0.75
    erry
    -0.71
    lyss
    -0.70
     Asians
    -0.69
    hig
    -0.69
    native
    -0.69
    inet
    -0.69
    Cry
    -0.68
    ahime
    -0.68
    POSITIVE LOGITS
     rotation
    0.90
     rotating
    0.87
     rotated
    0.83
     revolutions
    0.83
     rotate
    0.83
     axis
    0.82
     direction
    0.80
    ular
    0.79
    ational
    0.79
    arious
    0.75
    Act Density 0.010%

    No Known Activations