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

    Neuronpedia

    INDEX
    Explanations

    phrases describing entities or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.13
    3:0.07
    4:0.06
    5:0.04
    6:0.12
    7:0.15
    8:0.04
    9:0.04
    10:0.11
    11:0.15
    Negative Logits
    raq
    -1.61
     nutshell
    -1.41
     shove
    -1.40
    ivot
    -1.38
     conventions
    -1.35
     Samoa
    -1.34
     guess
    -1.31
     compliment
    -1.30
     deserts
    -1.29
     reservations
    -1.28
    POSITIVE LOGITS
    MpServer
    1.76
    Winged
    1.42
    >]
    1.41
    GGGGGGGG
    1.35
    ertodd
    1.34
     sidx
    1.32
    BuyableInstoreAndOnline
    1.32
    ATURES
    1.30
    yx
    1.30
    possibly
    1.30
    Act Density 0.001%

    No Known Activations