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

    Neuronpedia

    INDEX
    Explanations

    references to the mouth and its various actions and states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apot
    -0.18
    hip
    -0.18
    estruct
    -0.17
    nave
    -0.16
    pole
    -0.16
    /load
    -0.15
    rib
    -0.15
    oval
    -0.14
    uars
    -0.14
    cial
    -0.14
    POSITIVE LOGITS
    -mouth
    0.22
     mouth
    0.18
    mouth
    0.18
     Bucc
    0.17
    æ¡£
    0.17
     mouths
    0.16
     Mouth
    0.15
    -face
    0.15
    ouden
    0.15
    nge
    0.15
    Act Density 0.067%

    No Known Activations