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

    Neuronpedia

    INDEX
    Explanations

    terms related to facial features or facial actions, especially those involving emotion or communication

    oai_token-act-pair · gpt-3.5-turbo

    references to facial characteristics or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mate
    -0.68
     grandfather
    -0.64
     subp
    -0.64
     Provided
    -0.64
     husband
    -0.61
     undone
    -0.60
     Passage
    -0.60
     Slug
    -0.59
     grandson
    -0.59
     brother
    -0.58
    POSITIVE LOGITS
    ilitation
    1.41
    ulty
    1.32
    eless
    1.31
    ilit
    1.29
    ilitating
    1.27
    etime
    1.26
    ework
    1.22
    ility
    1.17
    ilities
    1.17
    sim
    1.14
    Act Density 0.039%

    No Known Activations