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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty or questioning about the truth of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardon
    -0.17
    iero
    -0.14
    ÑĢеменно
    -0.14
    æ»
    -0.14
    ัà¸ļร
    -0.14
     æĺ¥
    -0.14
    odo
    -0.13
    oub
    -0.13
    alytics
    -0.13
    .yy
    -0.13
    POSITIVE LOGITS
     turns
    0.76
     turned
    0.68
     turn
    0.66
     Turns
    0.63
    Turn
    0.62
    turn
    0.61
     Turn
    0.60
    turned
    0.58
    -turn
    0.56
     TURN
    0.52
    Act Density 0.251%

    No Known Activations