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

    Neuronpedia

    INDEX
    Explanations

    phrases that express certainty or determination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    link
    -0.14
    ÏĦια
    -0.14
    ths
    -0.14
    íijľ
    -0.13
    OWN
    -0.13
     fut
    -0.13
     unbe
    -0.13
    YRO
    -0.13
    ISK
    -0.13
    irs
    -0.13
    POSITIVE LOGITS
     time
    0.22
     lights
    0.21
     curtains
    0.19
     business
    0.19
    Lights
    0.19
     Lights
    0.18
     game
    0.18
     GAME
    0.18
    business
    0.17
    lights
    0.17
    Act Density 0.088%

    No Known Activations