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

    Neuronpedia

    INDEX
    Explanations

    articles and modifiers used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.13
    3:0.08
    4:0.10
    5:0.02
    6:0.28
    7:0.14
    8:0.04
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
    nai
    -1.46
    yles
    -1.37
    �
    -1.36
    kamp
    -1.31
    icro
    -1.30
     unfocusedRange
    -1.29
    isky
    -1.28
    ophon
    -1.27
     peacefully
    -1.27
    SHIP
    -1.25
    POSITIVE LOGITS
    TPPStreamerBot
    1.46
     Kinnikuman
    1.38
    earances
    1.38
    psey
    1.28
    ament
    1.25
    Footnote
    1.24
    stood
    1.22
    replace
    1.21
    comings
    1.20
    -------
    1.19
    Act Density 0.000%

    No Known Activations