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

    Neuronpedia

    INDEX
    Explanations

    words and phrases describing negative emotions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ç¡
    -0.06
    enne
    -0.06
    antu
    -0.06
     lastIndex
    -0.06
    orst
    -0.06
    à¸Ľà¸£à¸°à¸ª
    -0.06
    FromClass
    -0.06
    ounsel
    -0.06
    04
    -0.06
    andel
    -0.06
    POSITIVE LOGITS
     relief
    0.07
     concern
    0.07
    uby
    0.07
     mixed
    0.07
    ustr
    0.06
     AN
    0.06
    dings
    0.06
     feelings
    0.06
    anger
    0.06
     Infer
    0.06
    Act Density 0.017%

    No Known Activations