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

    Neuronpedia

    INDEX
    Explanations

    references to eye contact and physical expressions indicating attention or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ustimmung
    -0.69
    SCRIBE
    -0.62
     Akismet
    -0.61
     Stroh
    -0.60
     nemlig
    -0.60
    parsedMessage
    -0.60
    RenderAtEndOf
    -0.59
    transQ
    -0.59
     Audiodateien
    -0.59
     Cæsar
    -0.58
    POSITIVE LOGITS
     faces
    0.57
     towards
    0.53
     toward
    0.49
     trùng
    0.46
     face
    0.46
    empty
    0.46
    faces
    0.45
    blank
    0.45
     hacia
    0.44
     Faces
    0.44
    Act Density 0.086%

    No Known Activations