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

    Neuronpedia

    INDEX
    Explanations

    contractions and abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    elements of speculation and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angering
    -0.61
     exting
    -0.60
    VERTISEMENT
    -0.59
    Ý
    -0.58
    etermined
    -0.58
    è¦ļéĨĴ
    -0.57
     volunte
    -0.55
    ordable
    -0.55
    entials
    -0.55
    umerous
    -0.55
    POSITIVE LOGITS
     Hermione
    0.89
     Jaune
    0.82
     Snape
    0.81
     Voldemort
    0.79
     yeah
    0.78
     Gohan
    0.78
     Dumbledore
    0.78
     Rowling
    0.78
     Shinji
    0.76
     Naruto
    0.76
    Act Density 0.711%

    No Known Activations