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

    Neuronpedia

    INDEX
    Explanations

    proper nouns associated with different individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.90
    ruary
    -0.85
    Reviewer
    -0.80
    ModLoader
    -0.76
    Posted
    -0.67
    taboola
    -0.66
    fml
    -0.65
    =]
    -0.64
    éĹĺ
    -0.63
    æ©
    -0.63
    POSITIVE LOGITS
    opol
    0.73
     Khan
    0.71
    ciating
    0.71
    kh
    0.70
    asy
    0.68
    opian
    0.66
     Kov
    0.65
    iple
    0.64
     Pok
    0.63
    udi
    0.62
    Act Density 0.107%

    No Known Activations