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

    Neuronpedia

    INDEX
    Explanations

    phrases describing degrees or measurements of various attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izop
    -0.86
    Dum
    -0.71
     Selby
    -0.68
     Şi
    -0.67
     Dum
    -0.67
     muzik
    -0.67
     gelassen
    -0.67
    spoken
    -0.66
    pit
    -0.65
    voor
    -0.65
    POSITIVE LOGITS
     degrees
    1.82
     degree
    1.76
     Degrees
    1.73
     Degree
    1.66
     DEGREE
    1.60
    Degree
    1.57
    degree
    1.55
    Degrees
    1.52
    degrees
    1.52
    GREES
    1.35
    Act Density 0.089%

    No Known Activations