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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments and expressions of disappointment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enever
    -0.15
     normally
    -0.15
    normally
    -0.14
     reaff
    -0.14
    zers
    -0.14
    nika
    -0.13
    Oi
    -0.13
    HEY
    -0.13
    tsy
    -0.13
    eldom
    -0.13
    POSITIVE LOGITS
    cola
    0.17
     fabulous
    0.16
    é¼
    0.15
    avig
    0.14
     xo
    0.14
     Tort
    0.14
    ammen
    0.14
     lovely
    0.14
    Calibri
    0.13
    Ł
    0.13
    Act Density 0.009%

    No Known Activations