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

    Neuronpedia

    INDEX
    Explanations

    instances of movement or action verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ording
    -0.17
    änger
    -0.14
    ield
    -0.14
    ddf
    -0.14
    inkel
    -0.13
     interchange
    -0.13
    ko
    -0.13
    luv
    -0.13
    kommen
    -0.13
    airo
    -0.13
    POSITIVE LOGITS
     charging
    0.24
     looking
    0.23
     bounding
    0.21
     bol
    0.18
     tum
    0.18
    looking
    0.18
     gal
    0.17
     Charging
    0.17
     around
    0.17
     Looking
    0.17
    Act Density 0.135%

    No Known Activations