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

    Neuronpedia

    INDEX
    Explanations

    references to educational institutions and their policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.02
    2:0.08
    3:0.03
    4:0.05
    5:0.03
    6:0.26
    7:0.03
    8:0.05
    9:0.21
    10:0.02
    11:0.04
    Negative Logits
     Ov
    -4.20
     ovarian
    -4.07
     ov
    -3.83
    Johnny
    -3.82
     arom
    -3.61
     Reboot
    -3.56
     metabol
    -3.52
    Dub
    -3.41
    Av
    -3.30
    gran
    -3.28
    POSITIVE LOGITS
     Teacher
    8.13
     teachers
    7.75
     teacher
    7.72
     Teachers
    7.61
     Teach
    7.05
     Teaching
    6.71
     teaching
    5.87
     educators
    5.67
     teach
    5.62
     educator
    5.43
    Act Density 0.017%

    No Known Activations