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

    Neuronpedia

    INDEX
    Explanations

    expressions of disappointment or misfortune

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressing misfortune

    np_acts-logits-general · gemini-2.0-flash

    fortunate and unfortunate outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     definitely
    -0.68
    definitely
    -0.68
    campista
    -0.63
     surely
    -0.63
     ?>>
    -0.63
    そりゃ
    -0.63
     certainly
    -0.61
     why
    -0.60
     Pourquoi
    -0.59
     Definitely
    -0.59
    POSITIVE LOGITS
    erweise
    0.85
     enough
    0.72
     genoeg
    0.66
     also
    0.66
    enough
    0.65
    (?)
    0.64
     (?)
    0.63
     none
    0.62
     estimés
    0.62
     Unlike
    0.60
    Act Density 0.193%

    No Known Activations