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

    Neuronpedia

    INDEX
    Explanations

    references to the mouth and actions involving it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otas
    -0.18
    Picker
    -0.18
    apot
    -0.17
    estruct
    -0.16
    ildo
    -0.16
    uars
    -0.15
    apl
    -0.15
    alars
    -0.15
    .qq
    -0.14
    grounds
    -0.14
    POSITIVE LOGITS
    -mouth
    0.23
    mouth
    0.20
     mouth
    0.17
     Bucc
    0.16
    soever
    0.15
     invol
    0.14
    ache
    0.14
    æ¡£
    0.14
    {text
    0.14
    Photon
    0.14
    Act Density 0.040%

    No Known Activations