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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases and locational indicators in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.10
    3:0.07
    4:0.09
    5:0.03
    6:0.05
    7:0.32
    8:0.04
    9:0.05
    10:0.11
    11:0.06
    Negative Logits
    angler
    -1.58
     stalls
    -1.56
     funnel
    -1.46
     tamp
    -1.37
     Hansen
    -1.32
     horns
    -1.31
    utt
    -1.31
     Fib
    -1.30
     distributor
    -1.29
    pend
    -1.29
    POSITIVE LOGITS
    Privacy
    1.63
    EMBER
    1.55
    oyal
    1.54
    Friend
    1.48
    Priv
    1.43
    龍喚士
    1.41
     Friendship
    1.41
    INESS
    1.41
    IGN
    1.40
    Justice
    1.39
    Act Density 0.000%

    No Known Activations