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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expectations or obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.98
     myſelf
    -0.93
     Efq
    -0.92
     pleaſure
    -0.83
    kháu
    -0.81
     Jefus
    -0.81
     fince
    -0.80
     BoxDecoration
    -0.78
     poffe
    -0.77
     themſelves
    -0.77
    POSITIVE LOGITS
     supposed
    1.58
    supposed
    1.30
     supposedly
    0.99
     meant
    0.98
     suppose
    0.92
     supuestamente
    0.78
    meant
    0.77
     intended
    0.73
     suppos
    0.71
     should
    0.69
    Act Density 0.124%

    No Known Activations