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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and phrases indicating statements or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.02
    2:0.08
    3:0.05
    4:0.05
    5:0.04
    6:0.19
    7:0.05
    8:0.13
    9:0.17
    10:0.03
    11:0.03
    Negative Logits
     omn
    -4.02
    apeake
    -3.48
     Negro
    -3.47
     Archangel
    -3.38
     Syndicate
    -3.38
    reen
    -3.35
     Okin
    -3.35
    shield
    -3.31
     Dominion
    -3.31
    Unity
    -3.22
    POSITIVE LOGITS
     Bie
    11.40
     Bieber
    9.02
     Bubble
    4.41
     Gaga
    4.39
     Ange
    4.39
     Braun
    4.30
     Celeb
    4.13
     Spears
    4.11
     Bild
    4.11
     Tuc
    4.07
    Act Density 0.001%

    No Known Activations