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

    Neuronpedia

    INDEX
    Explanations

    names related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    names and references to individuals and groups in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #$
    -0.92
    lder
    -0.86
    quote
    -0.75
    lde
    -0.71
    manship
    -0.71
    swing
    -0.70
    Cola
    -0.70
    Ħ¢
    -0.70
    stocks
    -0.68
    ball
    -0.67
    POSITIVE LOGITS
    opoulos
    0.84
     Ukrain
    0.80
     Valent
    0.78
    avia
    0.77
    onis
    0.75
    akov
    0.74
     Alexand
    0.72
    inite
    0.72
    rina
    0.72
    opol
    0.71
    Act Density 0.008%

    No Known Activations