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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.06
    3:0.05
    4:0.16
    5:0.02
    6:0.23
    7:0.07
    8:0.04
    9:0.03
    10:0.09
    11:0.16
    Negative Logits
    lins
    -1.36
     Clarkson
    -1.27
     Aless
    -1.27
     understatement
    -1.26
     routed
    -1.25
     Levant
    -1.23
     Fired
    -1.23
     newsletter
    -1.23
     Heist
    -1.22
     Emin
    -1.21
    POSITIVE LOGITS
    ascript
    1.57
    asus
    1.56
    ukong
    1.50
    Rat
    1.47
     Flavoring
    1.46
    sites
    1.42
    do
    1.40
    annabin
    1.33
    ritic
    1.32
    develop
    1.31
    Act Density 0.001%

    No Known Activations