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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.07
    2:0.06
    3:0.10
    4:0.12
    5:0.13
    6:0.08
    7:0.02
    8:0.10
    9:0.12
    10:0.07
    11:0.02
    Negative Logits
     gol
    -1.38
     kinderg
    -1.38
    �
    -1.27
     Helic
    -1.18
     tru
    -1.17
     unconscious
    -1.16
     gra
    -1.16
    duc
    -1.16
     weap
    -1.13
     Nou
    -1.13
    POSITIVE LOGITS
    tymology
    1.48
    itars
    1.44
     meanwhile
    1.42
    culosis
    1.42
    igree
    1.40
    anwhile
    1.39
    quartered
    1.39
     contrasts
    1.38
    sequently
    1.38
    erton
    1.34
    Act Density 0.046%

    No Known Activations