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

    Neuronpedia

    INDEX
    Explanations

    words conveying uncertainty or questioning expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hob
    -0.16
    ouser
    -0.15
    odb
    -0.15
    _REPLACE
    -0.14
    olec
    -0.14
    åĽ
    -0.14
     responseObject
    -0.13
    æħİ
    -0.13
    quared
    -0.13
    ono
    -0.13
    POSITIVE LOGITS
    ilia
    0.15
    Extras
    0.15
    ä¾
    0.15
     impover
    0.14
    emens
    0.14
    ừa
    0.14
    vou
    0.14
     opaque
    0.13
    noch
    0.13
    çªģ
    0.13
    Act Density 0.004%

    No Known Activations