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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mbH
    -0.17
    .sul
    -0.16
    اÙĪرÛĮ
    -0.15
     hakk
    -0.15
    umba
    -0.15
     kop
    -0.14
    oleÄį
    -0.14
    efeller
    -0.14
    ronym
    -0.13
    ³
    -0.13
    POSITIVE LOGITS
    upe
    0.16
     inst
    0.15
    etu
    0.15
    é¡Ķ
    0.15
    ekl
    0.15
    Pie
    0.15
     adm
    0.15
    eh
    0.14
    /tutorial
    0.14
     Tone
    0.14
    Act Density 0.062%

    No Known Activations