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

    Neuronpedia

    INDEX
    Explanations

    questions and requests for clarification or input

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     faptul
    -0.65
     للاسماء
    -0.63
     defire
    -0.54
     Unies
    -0.53
     EnglishChoose
    -0.53
    nationality
    -0.53
    Espèce
    -0.52
     rè
    -0.52
     Rov
    -0.52
     Wraith
    -0.51
    POSITIVE LOGITS
    .*")]
    0.68
     coincidence
    0.62
    sisting
    0.58
    celess
    0.57
    gapan
    0.57
     coincide
    0.55
    AnimationsModule
    0.54
    nelli
    0.53
    nommen
    0.53
    poptosis
    0.52
    Act Density 0.060%

    No Known Activations