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

    Neuronpedia

    INDEX
    Explanations

    references to the mouth and related oral activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (;;)
    -0.96
     يتيمه
    -0.87
    logrus
    -0.73
     Stefanie
    -0.69
    hasMoreElements
    -0.68
    logram
    -0.66
    νι
    -0.65
     Hald
    -0.65
     BCM
    -0.65
    TextBoxColumn
    -0.64
    POSITIVE LOGITS
     Mouth
    1.60
     mouth
    1.55
    Mouth
    1.39
     mouths
    1.30
     teeth
    1.23
     Teeth
    1.22
    mouth
    1.18
     Tooth
    1.17
     lips
    1.15
     Lips
    1.13
    Act Density 0.159%

    No Known Activations