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

    Neuronpedia

    INDEX
    Explanations

    references to regulatory processes and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ³³
    -0.20
     Swim
    -0.17
     swim
    -0.15
    ÅĽci
    -0.15
    éŃļ
    -0.14
     surf
    -0.14
    odon
    -0.14
     ä½ı
    -0.14
    _UD
    -0.14
    inski
    -0.14
    POSITIVE LOGITS
     IMO
    0.35
    IMO
    0.31
     Flag
    0.26
     MAR
    0.26
     tanker
    0.26
     flag
    0.25
     SOL
    0.25
     cargo
    0.24
     carriage
    0.24
     crew
    0.24
    Act Density 0.019%

    No Known Activations