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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating simplicity or ease of use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -1.05
    WireFormatLite
    -1.04
    RegistryLite
    -1.00
     ProtoMessage
    -0.98
    AndEndTag
    -0.95
    bootstrapcdn
    -0.94
     GenerationType
    -0.93
     AspNetCore
    -0.92
     kasarigan
    -0.91
     StatelessWidget
    -0.91
    POSITIVE LOGITS
     Easy
    1.52
     easy
    1.51
    Easy
    1.48
     EASY
    1.45
    EASY
    1.40
     Eas
    1.37
     EAS
    1.32
    easy
    1.32
     easily
    1.25
     eas
    1.24
    Act Density 0.097%

    No Known Activations