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

    Neuronpedia

    INDEX
    Explanations

    references to communities and groups within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     messing
    -0.56
     gonna
    -0.52
     heißt
    -0.50
     freaked
    -0.50
     messes
    -0.46
     messed
    -0.46
     stops
    -0.46
     novedad
    -0.45
    มัน
    -0.45
     sucks
    -0.45
    POSITIVE LOGITS
     view
    0.70
     possess
    0.66
     possesses
    0.65
    poss
    0.65
     views
    0.62
     seek
    0.60
     posses
    0.58
     perceive
    0.57
     viewed
    0.57
     viewing
    0.57
    Act Density 0.979%

    No Known Activations