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

    Neuronpedia

    INDEX
    Explanations

    references to body posture or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EDI
    -0.16
    edy
    -0.16
    aby
    -0.15
    eyed
    -0.15
    edi
    -0.15
     Birch
    -0.15
    yun
    -0.14
    гÑĥ
    -0.14
    haus
    -0.14
    Boot
    -0.14
    POSITIVE LOGITS
     shoulders
    0.74
     shoulder
    0.72
     Shoulder
    0.60
    èĤ©
    0.52
     плеÑĩ
    0.45
    should
    0.38
    Should
    0.36
     Should
    0.34
     neck
    0.30
    .Should
    0.30
    Act Density 0.068%

    No Known Activations