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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.03
    3:0.28
    4:0.02
    5:0.03
    6:0.05
    7:0.16
    8:0.03
    9:0.12
    10:0.08
    11:0.10
    Negative Logits
    entimes
    -1.30
     outweigh
    -1.30
    reau
    -1.29
    imentary
    -1.25
    athy
    -1.25
    ibling
    -1.24
    iew
    -1.22
    ounters
    -1.21
    rollers
    -1.20
    ighting
    -1.17
    POSITIVE LOGITS
     Machina
    1.47
     deaf
    1.25
     Eston
    1.21
     dystop
    1.17
     phrase
    1.16
     anarch
    1.11
     phrases
    1.08
     Korra
    1.05
     jur
    1.03
     android
    1.03
    Act Density 0.005%

    No Known Activations