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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names with a particular set of special characters (Ċ)

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical and citation-like formatting, indicating references or sources in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.63
     dissu
    -0.62
     intervening
    -0.59
     restitution
    -0.59
     Pompe
    -0.58
     overth
    -0.57
    ivably
    -0.56
    adish
    -0.56
     revocation
    -0.56
     antit
    -0.55
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    1.04
    ³³³³³³³³
    0.99
    ³³³
    0.91
    ³³³³
    0.90
    ³³
    0.82
    Posted
    0.81
    Disclaimer
    0.80
    Guest
    0.80
    Edit
    0.79
    Contents
    0.75
    Act Density 0.178%

    No Known Activations