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

    Neuronpedia

    INDEX
    Explanations

    references to rationality or rational behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     costs
    -0.54
     Costs
    -0.50
     Ben
    -0.46
     Erd
    -0.46
     Pay
    -0.45
     Cost
    -0.43
     Đ
    -0.43
     Pop
    -0.43
     Har
    -0.43
     Pen
    -0.42
    POSITIVE LOGITS
    MigrationBuilder
    0.69
     Majefty
    0.69
     <<<<<<<<<<<<<<
    0.67
    featureID
    0.66
     normalidad
    0.66
     itſelf
    0.65
     zijne
    0.64
     informée
    0.63
     Auftritt
    0.63
     mukana
    0.61
    Act Density 0.288%

    No Known Activations