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

    Neuronpedia

    INDEX
    Explanations

    references to hands and their movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .connector
    -0.15
     Tops
    -0.15
     flank
    -0.15
     sideways
    -0.14
    standing
    -0.14
    stal
    -0.14
     standing
    -0.14
    swer
    -0.14
     Leather
    -0.14
    uron
    -0.14
    POSITIVE LOGITS
    orget
    0.16
    Fcn
    0.15
     pump
    0.14
     pumping
    0.14
    biz
    0.14
    iday
    0.14
    540
    0.14
     Hamp
    0.14
    maid
    0.14
    enido
    0.13
    Act Density 0.091%

    No Known Activations