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

    Neuronpedia

    INDEX
    Explanations

    terms related to oral and sexual activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (;;)
    -0.81
     يتيمه
    -0.78
    TextBoxColumn
    -0.70
     intptr
    -0.70
    logram
    -0.69
     Stefanie
    -0.68
    OGND
    -0.68
    logrus
    -0.67
     escarp
    -0.67
    transQ
    -0.65
    POSITIVE LOGITS
     Mouth
    1.69
     mouth
    1.66
    Mouth
    1.49
     mouths
    1.35
    mouth
    1.27
     lips
    1.25
     Lips
    1.21
     oral
    1.17
     teeth
    1.15
     bouche
    1.14
    Act Density 0.174%

    No Known Activations