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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     far
    -0.15
    annes
    -0.15
    bow
    -0.15
    무
    -0.14
     rather
    -0.14
     Nap
    -0.14
    far
    -0.14
     confirmation
    -0.14
    cott
    -0.14
    exampleModal
    -0.14
    POSITIVE LOGITS
    uce
    0.18
    Ñģли
    0.15
    ucus
    0.15
    isse
    0.15
    unger
    0.14
    _AUX
    0.14
    ture
    0.14
    æĬ¼
    0.14
    å±Ĩ
    0.14
    uces
    0.14
    Act Density 0.138%

    No Known Activations