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

    Neuronpedia

    INDEX
    Explanations

    names of individuals from various contexts or articles

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nian
    -0.63
    jriwal
    -0.60
     amateur
    -0.56
     Reincarn
    -0.55
     honesty
    -0.55
    sed
    -0.55
     adoptive
    -0.55
     legislatures
    -0.54
     emergencies
    -0.54
     "#
    -0.54
    POSITIVE LOGITS
    ñ
    1.36
    uthor
    1.27
    eus
    1.20
    issance
    1.17
    ño
    1.17
    ña
    1.17
    ï
    1.12
    fter
    1.10
    ver
    1.10
    vel
    1.07
    Act Density 0.176%

    No Known Activations