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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or locations in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oka
    -1.01
    ox
    -0.92
     LX
    -0.87
    OX
    -0.85
    opl
    -0.82
    omy
    -0.82
     TAMADRA
    -0.81
     Norwich
    -0.80
    WP
    -0.79
    710
    -0.79
    POSITIVE LOGITS
    de
    1.16
    des
    1.02
     Mul
    1.02
    Del
    1.02
     Des
    0.99
     De
    0.98
    De
    0.96
    DE
    0.95
     Dul
    0.94
    DEM
    0.94
    Act Density 0.413%

    No Known Activations