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

    Neuronpedia

    INDEX
    Explanations

    pronouns indicating people, particularly emphasizing "they" and "he"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     langue
    -0.63
    FieldNumber
    -0.60
     conventional
    -0.55
     procedere
    -0.52
     noires
    -0.51
    estable
    -0.51
    Traducción
    -0.51
     PAZ
    -0.51
     skle
    -0.51
    INN
    -0.50
    POSITIVE LOGITS
    tvguidetime
    0.76
     hâte
    0.76
    TestBed
    0.69
    InputTagHelper
    0.68
    tagHelperRunner
    0.68
    ConstraintMaker
    0.67
    SizeMode
    0.67
     noten
    0.67
     TextInputType
    0.65
    WebServlet
    0.65
    Act Density 0.150%

    No Known Activations