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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.13
    2:0.06
    3:0.10
    4:0.08
    5:0.12
    6:0.07
    7:0.02
    8:0.04
    9:0.11
    10:0.12
    11:0.06
    Negative Logits
    Scope
    -1.53
    Swe
    -1.48
    Merc
    -1.46
    Ele
    -1.43
    overe
    -1.40
    cha
    -1.37
    �
    -1.36
    ai
    -1.36
    odi
    -1.36
    Pan
    -1.35
    POSITIVE LOGITS
    culosis
    1.53
     fooled
    1.51
    gettable
    1.50
    quartered
    1.49
     PHOTO
    1.46
     Pwr
    1.46
    tymology
    1.44
     filming
    1.44
     Photograph
    1.43
     posed
    1.40
    Act Density 0.050%

    No Known Activations