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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to questioning and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ´²
    -0.15
     Frid
    -0.14
    uce
    -0.14
    undy
    -0.14
     åģ
    -0.14
    pone
    -0.14
    duk
    -0.13
    elong
    -0.13
    姿
    -0.13
    lify
    -0.13
    POSITIVE LOGITS
     we
    0.26
     appears
    0.21
     seems
    0.20
     happened
    0.20
     is
    0.19
     happens
    0.19
    -ÑĤо
    0.19
     appear
    0.18
     might
    0.18
     seem
    0.17
    Act Density 0.078%

    No Known Activations