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

    Neuronpedia

    INDEX
    Explanations

    punctuation and narrative transitions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.02
    2:0.07
    3:0.04
    4:0.05
    5:0.04
    6:0.26
    7:0.04
    8:0.07
    9:0.23
    10:0.02
    11:0.04
    Negative Logits
    ugu
    -4.31
     Rw
    -3.91
     Yug
    -3.87
     blender
    -3.87
    vol
    -3.76
    grad
    -3.66
     gor
    -3.57
     monkeys
    -3.56
     dolphin
    -3.55
     guitars
    -3.52
    POSITIVE LOGITS
     Heath
    11.12
     Hots
    4.43
     AH
    4.24
     Meadow
    3.94
    Beck
    3.93
     Hick
    3.92
     Ike
    3.87
     Cind
    3.86
     Hamp
    3.83
     Bethlehem
    3.82
    Act Density 0.001%

    No Known Activations