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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong emotions, opinions, or personal attachments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utin
    -0.16
     Coch
    -0.15
     Ste
    -0.15
    lamaz
    -0.14
     Conway
    -0.14
     Kami
    -0.14
     Nimbus
    -0.14
    (rad
    -0.14
    urd
    -0.14
    _ACK
    -0.14
    POSITIVE LOGITS
     THAT
    0.23
    atsu
    0.19
    oes
    0.16
    éĤ£æł·
    0.15
    ết
    0.15
    _that
    0.15
     ÑĤого
    0.15
    ãĥ¼ãĥŃ
    0.15
    caption
    0.14
    äter
    0.14
    Act Density 0.108%

    No Known Activations