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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships between events and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.05
    3:0.05
    4:0.11
    5:0.02
    6:0.40
    7:0.13
    8:0.04
    9:0.03
    10:0.06
    11:0.04
    Negative Logits
    SPONSORED
    -1.43
    FORE
    -1.35
    QL
    -1.34
    ICAN
    -1.34
    TION
    -1.34
    gdala
    -1.32
    soever
    -1.31
    ONSORED
    -1.31
     Dhabi
    -1.30
     hereafter
    -1.30
    POSITIVE LOGITS
    thur
    1.67
     punches
    1.48
     fingers
    1.46
     scissors
    1.43
    wards
    1.38
     desks
    1.38
    auntlet
    1.36
     bead
    1.34
    eper
    1.33
    enged
    1.32
    Act Density 0.173%

    No Known Activations