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

    Neuronpedia

    INDEX
    Explanations

    words related to automated code generation and programming comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.86
     Monfieur
    -0.83
     Diſ
    -0.81
     Eſ
    -0.80
     ſeveral
    -0.79
     Anſ
    -0.79
     myſelf
    -0.78
     Conſ
    -0.78
     Efq
    -0.77
     houſe
    -0.77
    POSITIVE LOGITS
    generated
    1.53
     generated
    1.00
    OGND
    0.74
     generate
    0.73
     AssemblyCompany
    0.67
     للمعارف
    0.64
     generado
    0.63
     generation
    0.62
     Generated
    0.62
    generate
    0.62
    Act Density 0.014%

    No Known Activations