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

    Neuronpedia

    INDEX
    Explanations

    references to walking or movement actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nestjs
    -0.16
    erie
    -0.15
    ола
    -0.15
    ingleton
    -0.15
    pers
    -0.14
    _DL
    -0.14
    ืà¹ī
    -0.14
    edy
    -0.14
    ijke
    -0.14
     باÙĦÙĨ
    -0.14
    POSITIVE LOGITS
     walk
    0.24
    walk
    0.24
     Walk
    0.23
    Walk
    0.21
     walked
    0.21
    .walk
    0.20
     away
    0.20
     tall
    0.20
     walks
    0.19
    -talk
    0.19
    Act Density 0.025%

    No Known Activations