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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating research or exploration of topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.04
    2:0.11
    3:0.08
    4:0.06
    5:0.06
    6:0.04
    7:0.03
    8:0.23
    9:0.14
    10:0.06
    11:0.03
    Negative Logits
    "]=>
    -1.38
    uploads
    -1.29
    ''.
    -1.26
    ucci
    -1.21
     WARN
    -1.20
    leon
    -1.15
    enko
    -1.10
     inherit
    -1.09
     Chairman
    -1.09
    warn
    -1.04
    POSITIVE LOGITS
    igm
    1.25
    raph
    1.23
    isine
    1.23
    otrop
    1.22
     hobbies
    1.20
     canv
    1.19
    requency
    1.15
    aband
    1.15
     enthus
    1.11
     sqor
    1.11
    Act Density 0.009%

    No Known Activations