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

    Neuronpedia

    INDEX
    Explanations

    named characters in the context of stories or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.63
    NUMX
    -0.47
    OwnProperty
    -0.47
     متعلقه
    -0.47
    onnaissance
    -0.46
    Autoritní
    -0.46
    <h6>
    -0.45
    blet
    -0.44
    "?>
    -0.44
     communiquez
    -0.44
    POSITIVE LOGITS
     wakes
    0.64
     kapit
    0.62
     awoke
    0.61
     karakter
    0.60
     cosplay
    0.60
     awakens
    0.60
     فريبيس
    0.58
     discovers
    0.58
     woken
    0.57
     character
    0.57
    Act Density 0.250%

    No Known Activations