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

    Neuronpedia

    INDEX
    Explanations

    phrases indicative of quotes or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.02
    2:0.07
    3:0.03
    4:0.05
    5:0.03
    6:0.26
    7:0.04
    8:0.07
    9:0.24
    10:0.01
    11:0.05
    Negative Logits
     Diver
    -3.91
     cod
    -3.85
     TAG
    -3.67
     fisher
    -3.64
     Lizard
    -3.62
     Cyborg
    -3.62
    Cod
    -3.57
    cod
    -3.50
     Nets
    -3.45
     Hod
    -3.43
    POSITIVE LOGITS
    Pa
    9.23
     Pa
    9.14
     Paige
    6.99
     PA
    6.38
    pa
    6.22
     pa
    5.81
     Pennsylvania
    5.64
    Penn
    5.64
    PA
    5.49
     Penn
    4.79
    Act Density 0.006%

    No Known Activations