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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the release of reports or surveys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.03
    2:0.16
    3:0.04
    4:0.02
    5:0.05
    6:0.06
    7:0.18
    8:0.08
    9:0.09
    10:0.11
    11:0.09
    Negative Logits
    rish
    -1.13
    rendered
    -1.03
    angan
    -1.03
    orship
    -1.01
    rex
    -1.00
    idon
    -0.98
    akuya
    -0.97
    osta
    -0.95
    nown
    -0.95
    bred
    -0.94
    POSITIVE LOGITS
    ebin
    1.30
    cloth
    1.10
     Qiao
    1.08
    actionDate
    1.06
     Downloads
    1.02
     surpr
    1.00
     previews
    0.98
     Lau
    0.95
     median
    0.94
    BuyableInstoreAndOnline
    0.93
    Act Density 0.045%

    No Known Activations