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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to media communication and dissemination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.00
    2:0.11
    3:0.08
    4:0.14
    5:0.02
    6:0.06
    7:0.30
    8:0.03
    9:0.03
    10:0.07
    11:0.09
    Negative Logits
    デ
    -1.48
     Relic
    -1.43
    ヘ
    -1.39
    asar
    -1.34
     Deity
    -1.33
     Idol
    -1.32
    avery
    -1.30
     Cf
    -1.30
    utterstock
    -1.27
    istine
    -1.26
    POSITIVE LOGITS
    覚醒
    1.76
    ERG
    1.58
     impending
    1.58
    DERR
    1.55
     leaflets
    1.54
     displeasure
    1.40
    ��
    1.36
    LEASE
    1.34
     distributors
    1.34
     loud
    1.31
    Act Density 0.005%

    No Known Activations