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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments and emotional expressions towards situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yeah
    -0.15
    icone
    -0.14
     Yeah
    -0.14
    lore
    -0.14
    icot
    -0.14
    ovÃŃ
    -0.14
    ìŀIJìĿ¸
    -0.14
    ewan
    -0.13
    enko
    -0.13
    inya
    -0.13
    POSITIVE LOGITS
     no
    0.26
     not
    0.22
     absolutely
    0.20
     sir
    0.20
     wait
    0.19
     seriously
    0.19
    -No
    0.19
    _no
    0.19
    -no
    0.18
     No
    0.18
    Act Density 0.038%

    No Known Activations