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

    Neuronpedia

    INDEX
    Explanations

    frequent appearance of high-impact television shows and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.08
    3:0.04
    4:0.07
    5:0.03
    6:0.38
    7:0.07
    8:0.03
    9:0.04
    10:0.10
    11:0.07
    Negative Logits
    velt
    -1.52
    kson
    -1.44
    Chan
    -1.38
    amiya
    -1.37
    ktop
    -1.34
    chan
    -1.31
    yers
    -1.29
     Aires
    -1.28
    ering
    -1.27
     Cree
    -1.26
    POSITIVE LOGITS
     prol
    1.48
     opener
    1.40
    ��
    1.37
     testament
    1.27
    BuyableInstoreAndOnline
    1.27
    ��
    1.24
     finale
    1.18
    ��
    1.18
     Judgment
    1.17
     Rankings
    1.14
    Act Density 0.009%

    No Known Activations