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

    Neuronpedia

    INDEX
    Explanations

    references to significant scientific concepts or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.06
    3:0.22
    4:0.12
    5:0.04
    6:0.04
    7:0.06
    8:0.05
    9:0.07
    10:0.13
    11:0.11
    Negative Logits
    luster
    -1.59
     enthusi
    -1.54
    acebook
    -1.53
     mosqu
    -1.52
    btn
    -1.47
    ateurs
    -1.43
    artifacts
    -1.31
    abilia
    -1.30
    gettable
    -1.28
    WARE
    -1.28
    POSITIVE LOGITS
    forth
    1.35
     op
    1.32
     cite
    1.30
     refers
    1.27
     supra
    1.26
     quoted
    1.25
     unpublished
    1.23
     FAQ
    1.19
     cited
    1.19
     noted
    1.19
    Act Density 0.003%

    No Known Activations