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

    Neuronpedia

    INDEX
    Explanations

    references to unity or collective experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.09
    2:0.08
    3:0.09
    4:0.07
    5:0.08
    6:0.07
    7:0.07
    8:0.09
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
    WASHINGTON
    -2.98
    cour
    -2.75
     Vander
    -2.73
    CLUD
    -2.67
    VID
    -2.57
    thirst
    -2.53
    Wil
    -2.52
    PHOTOS
    -2.52
     Vand
    -2.50
    width
    -2.47
    POSITIVE LOGITS
     Secondary
    3.08
    ?",
    2.60
     Edinburgh
    2.59
     realised
    2.52
     Stevenson
    2.47
     Secondly
    2.47
     Console
    2.40
     Kinect
    2.39
    Reviewer
    2.38
    AAA
    2.36
    Act Density 0.000%

    No Known Activations