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

    Neuronpedia

    INDEX
    Explanations

    phrases related to returning or coming back

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.09
    3:0.06
    4:0.16
    5:0.04
    6:0.06
    7:0.30
    8:0.04
    9:0.04
    10:0.05
    11:0.05
    Negative Logits
    ebook
    -1.71
    fax
    -1.54
    vernment
    -1.49
    enburg
    -1.48
     restrooms
    -1.48
    ometers
    -1.48
    ベ
    -1.45
    978
    -1.45
    window
    -1.43
     lookup
    -1.43
    POSITIVE LOGITS
     teasing
    1.46
     fact
    1.42
     Flav
    1.40
     sarc
    1.38
     Rampage
    1.35
    FU
    1.35
     Cheese
    1.33
     Suns
    1.32
     Till
    1.32
     Bans
    1.31
    Act Density 0.000%

    No Known Activations