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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing degrees of approximation or near certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ró
    -0.18
    orem
    -0.15
    uty
    -0.15
    lements
    -0.15
    /plain
    -0.15
    iÄĻ
    -0.15
    emmel
    -0.14
    athers
    -0.14
    .datas
    -0.14
    jug
    -0.14
    POSITIVE LOGITS
     entirely
    0.17
     exclusively
    0.16
    atical
    0.15
    arians
    0.15
    ny
    0.15
    ewan
    0.14
    avian
    0.14
    _NOTICE
    0.14
    æł·çļĦ
    0.13
    _almost
    0.13
    Act Density 0.024%

    No Known Activations