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

    Neuronpedia

    INDEX
    Explanations

    dates and numerical information

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iple
    -0.59
    ocl
    -0.52
    OND
    -0.50
     Crisis
    -0.50
    ction
    -0.50
    rage
    -0.48
    URE
    -0.47
    oret
    -0.47
     âĨ
    -0.47
    ongevity
    -0.47
    POSITIVE LOGITS
     respectively
    1.23
     etc
    0.98
     namely
    0.88
     thereby
    0.87
    anwhile
    0.85
     culminating
    0.84
     aka
    0.78
     whereas
    0.75
    thus
    0.73
    etc
    0.73
    Act Density 0.905%

    No Known Activations