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

    Neuronpedia

    INDEX
    Explanations

    code structures and functions related to parsing and processing data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dev
    -0.15
     addCriterion
    -0.14
    çŀ
    -0.14
     Hod
    -0.14
     Ah
    -0.14
    opers
    -0.14
    chooser
    -0.14
    .Prot
    -0.14
    Chooser
    -0.14
    веÑĢд
    -0.14
    POSITIVE LOGITS
    ConverterFactory
    0.15
     Convert
    0.15
    aley
    0.14
    afari
    0.14
    Convert
    0.14
    plib
    0.14
    Walk
    0.13
    pez
    0.13
    orr
    0.13
     Walk
    0.13
    Act Density 0.187%

    No Known Activations