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

    Neuronpedia

    INDEX
    Explanations

    actions related to positioning and assembling objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.17
     located
    -0.17
    -0.17
     ahead
    -0.16
     Ahead
    -0.15
    :
    -0.15
     exists
    -0.15
     Todd
    -0.15
     zoom
    -0.15
     knot
    -0.15
    POSITIVE LOGITS
     face
    0.21
     laying
    0.20
     faced
    0.20
     laid
    0.19
     FACE
    0.19
    supported
    0.18
     unsupported
    0.18
    LAY
    0.18
    дÑĢеÑģ
    0.18
    Supported
    0.18
    Act Density 0.117%

    No Known Activations