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

    Neuronpedia

    INDEX
    Explanations

    references to hard drives and printed materials such as books and covers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.04
    2:0.18
    3:0.07
    4:0.12
    5:0.08
    6:0.03
    7:0.02
    8:0.10
    9:0.10
    10:0.07
    11:0.03
    Negative Logits
    oshenko
    -1.67
     elig
    -1.40
    illard
    -1.39
    aucuses
    -1.28
    cand
    -1.27
    ��
    -1.26
    angel
    -1.24
    TPPStreamerBot
    -1.23
    irtual
    -1.22
    ulkan
    -1.21
    POSITIVE LOGITS
     reprint
    1.21
     Snape
    1.19
     reprinted
    1.17
     AGA
    1.16
     edited
    1.15
     Mustang
    1.13
     Malfoy
    1.12
    cery
    1.11
     Severus
    1.11
     SF
    1.08
    Act Density 0.007%

    No Known Activations