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

    Neuronpedia

    INDEX
    Explanations

    references to relationships and personal interactions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    himi
    -0.71
    +#+#
    -0.63
    #![
    -0.61
     Preserve
    -0.58
    χε
    -0.56
    Retention
    -0.56
    ianto
    -0.56
     parece
    -0.55
    IMPORTED
    -0.55
    ecs
    -0.54
    POSITIVE LOGITS
     للمعارف
    0.92
    tagext
    0.65
    PyExc
    0.55
    expandindo
    0.54
    (":");
    0.52
     derselbe
    0.50
     '\\;'
    0.50
    ()");
    0.49
    المناصب
    0.49
     TestBed
    0.49
    Act Density 0.116%

    No Known Activations