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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases pertaining to shapes and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.04
    2:0.17
    3:0.09
    4:0.09
    5:0.08
    6:0.03
    7:0.03
    8:0.06
    9:0.21
    10:0.07
    11:0.02
    Negative Logits
     Survivors
    -1.27
     Spartans
    -1.25
     Rebels
    -1.22
     bottled
    -1.20
     firsthand
    -1.20
     Revenge
    -1.19
    icipated
    -1.14
     incarcerated
    -1.14
    ilyn
    -1.14
     dearly
    -1.12
    POSITIVE LOGITS
    angular
    1.78
    shaped
    1.59
     encl
    1.47
    angle
    1.41
    Shape
    1.41
    ature
    1.38
    oid
    1.35
    dayName
    1.34
     delim
    1.33
     protr
    1.31
    Act Density 0.009%

    No Known Activations