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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names related to specific locations or individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific places and individuals, particularly associated with the names "Knox" and "Tate."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thal
    -0.92
    inating
    -0.79
    acter
    -0.73
    acted
    -0.71
    ination
    -0.71
    ULAR
    -0.70
    dfx
    -0.69
     Fi
    -0.69
    acting
    -0.69
    inated
    -0.68
    POSITIVE LOGITS
    ville
    0.92
    hift
    0.87
     Knox
    0.82
    terness
    0.82
    hyde
    0.81
    burgh
    0.80
    creen
    0.71
     millenn
    0.70
    chens
    0.70
    yle
    0.69
    Act Density 0.047%

    No Known Activations