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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people and places

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or entity name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ration
    -0.87
    gment
    -0.79
    ging
    -0.76
    mination
    -0.73
    veh
    -0.72
    aging
    -0.72
    rations
    -0.72
    outs
    -0.71
    eness
    -0.71
    tering
    -0.68
    POSITIVE LOGITS
    swer
    0.71
     "$:/
    0.71
    aic
    0.70
     NEXT
    0.68
    yip
    0.67
     Municip
    0.66
    iversal
    0.65
     Leilan
    0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.64
    iated
    0.63
    Act Density 0.258%

    No Known Activations