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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of knowledge or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.07
    3:0.09
    4:0.09
    5:0.07
    6:0.09
    7:0.08
    8:0.08
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
    pees
    -2.88
    ritch
    -2.57
     Blizz
    -2.42
    ��
    -2.32
     Cosponsors
    -2.30
    izoph
    -2.28
     strokes
    -2.28
    覚醒
    -2.27
     scen
    -2.20
    uckles
    -2.20
    POSITIVE LOGITS
     Syndicate
    3.34
     Skydragon
    2.90
     Pirate
    2.64
     Sov
    2.52
    nexus
    2.47
     Tasmania
    2.44
     Leilan
    2.40
     Pagan
    2.37
    proc
    2.32
     Mayhem
    2.31
    Act Density 0.000%

    No Known Activations