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

    Neuronpedia

    INDEX
    Explanations

    words related to spatial directions such as 'left' and 'right'

    oai_token-act-pair · gpt-3.5-turbo

    directional references in visual or spatial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensable
    -0.78
    eson
    -0.78
    etimes
    -0.72
    anned
    -0.71
    doms
    -0.71
    avorite
    -0.71
    NRS
    -0.69
    ocide
    -0.68
    olitics
    -0.67
    allo
    -0.67
    POSITIVE LOGITS
     side
    1.01
     hand
    0.99
     flank
    0.90
     corner
    0.86
     sidebar
    0.86
     hemisphere
    0.85
    most
    0.85
     paw
    0.83
     Side
    0.83
    ħĭ
    0.82
    Act Density 0.072%

    No Known Activations