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

    Neuronpedia

    INDEX
    Explanations

    phrases related to special summoning and powerful creatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.09
    3:0.16
    4:0.09
    5:0.04
    6:0.05
    7:0.10
    8:0.04
    9:0.07
    10:0.13
    11:0.12
    Negative Logits
     fame
    -1.41
     groom
    -1.33
    lain
    -1.28
     referrals
    -1.28
    romy
    -1.28
    bies
    -1.24
    MQ
    -1.23
     grooming
    -1.21
     lectures
    -1.21
    ◼
    -1.21
    POSITIVE LOGITS
    "]
    1.57
    .")
    1.48
    rike
    1.47
     SHALL
    1.40
    ":[
    1.40
    adium
    1.35
    )</
    1.34
     BALL
    1.34
    eping
    1.31
    aband
    1.28
    Act Density 0.001%

    No Known Activations