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

    Neuronpedia

    INDEX
    Explanations

    actions related to physical interactions and movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edor
    -0.20
    ingu
    -0.17
    obox
    -0.15
    idlo
    -0.15
     bez
    -0.14
    igon
    -0.14
     scream
    -0.14
    ÅĻÃŃd
    -0.14
    rido
    -0.14
    ãĥĦ
    -0.13
    POSITIVE LOGITS
    standing
    0.19
    ç«Ļ
    0.18
     stance
    0.18
     standing
    0.17
    Standing
    0.16
    -facing
    0.15
     facing
    0.15
    .motion
    0.15
    -standing
    0.15
    ancel
    0.15
    Act Density 0.194%

    No Known Activations