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

    Neuronpedia

    INDEX
    Explanations

    first person opinions and personal experiences

    oai_token-act-pair · gemini-2.0-flash

    phrases containing the pronoun 'I'

    np_token-act-pair-logits · gpt-4o-mini

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     دیکھیے
    -0.79
    RectangleBorder
    -0.71
     Biôgrafia
    -0.71
    Personensuche
    -0.70
    ">//
    -0.68
    ValueStyle
    -0.67
     pleaſure
    -0.66
    tanleria
    -0.66
     cref
    -0.65
    GOTREF
    -0.64
    POSITIVE LOGITS
     have
    0.49
    Addo
    0.49
     fisik
    0.47
    Shown
    0.46
    اعد
    0.44
     OnTriggerEnter
    0.42
     createState
    0.41
     Krieges
    0.41
     can
    0.40
    Poloha
    0.40
    Act Density 1.174%

    No Known Activations