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

    Neuronpedia

    INDEX
    Explanations

    specific attributes and functionalities of rowing machines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagon
    -0.17
    buzz
    -0.16
    Patch
    -0.15
    Buzz
    -0.15
    irie
    -0.15
    hack
    -0.14
    .patch
    -0.14
     Levin
    -0.14
    ema
    -0.14
    hq
    -0.14
    POSITIVE LOGITS
     grip
    0.55
     Grip
    0.46
     grips
    0.45
     gripping
    0.40
     gri
    0.40
     grasp
    0.38
     hold
    0.37
    hold
    0.35
    æı¡
    0.34
     gras
    0.34
    Act Density 0.101%

    No Known Activations