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

    Neuronpedia

    INDEX
    Explanations

    spatial references and directional cues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onda
    -0.17
    :both
    -0.16
    ocker
    -0.16
    ç¨
    -0.15
    locked
    -0.14
    лик
    -0.14
    exels
    -0.14
    ÙIJر
    -0.14
    ouser
    -0.14
    elight
    -0.14
    POSITIVE LOGITS
    -hand
    0.32
    ward
    0.28
    most
    0.26
     hand
    0.23
    wing
    0.22
    -wing
    0.21
    eous
    0.20
     wing
    0.20
    -side
    0.19
    -leaning
    0.19
    Act Density 0.041%

    No Known Activations