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

    Neuronpedia

    INDEX
    Explanations

    references to mental health and consent issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akis
    -0.21
     lug
    -0.17
    lug
    -0.15
     Downing
    -0.14
    lush
    -0.14
    aka
    -0.14
    ká
    -0.13
    esco
    -0.13
    ans
    -0.13
    rey
    -0.13
    POSITIVE LOGITS
    owler
    0.15
     fold
    0.15
    TOTYPE
    0.15
    [of
    0.14
     Rena
    0.14
    glob
    0.14
    aldi
    0.14
    azÄĥ
    0.14
    iona
    0.14
     Semi
    0.14
    Act Density 0.012%

    No Known Activations