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

    Neuronpedia

    INDEX
    Explanations

    actions and states related to positioning and storage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hma
    -0.16
    349
    -0.15
    .zoom
    -0.15
     adel
    -0.15
     ball
    -0.15
    lav
    -0.15
     paths
    -0.14
    ril
    -0.14
    aho
    -0.14
     am
    -0.14
    POSITIVE LOGITS
     faced
    0.23
     orientation
    0.23
     upside
    0.23
     face
    0.23
     orientations
    0.21
     facing
    0.21
     Orientation
    0.20
    orientation
    0.20
     upright
    0.19
    .face
    0.19
    Act Density 0.094%

    No Known Activations