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

    Neuronpedia

    INDEX
    Explanations

    imperative statements or warnings

    oai_token-act-pair · gpt-3.5-turbo

    imperative statements or warnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    figured
    -0.75
    ilogy
    -0.73
    potion
    -0.68
    ortment
    -0.67
    atar
    -0.67
    anded
    -0.66
    albeit
    -0.66
    alist
    -0.66
    ranch
    -0.65
    opened
    -0.64
    POSITIVE LOGITS
     yourselves
    1.10
     yourself
    1.03
     anymore
    1.01
     Yourself
    0.90
     whining
    0.78
     ANY
    0.78
     anything
    0.77
     any
    0.73
     your
    0.73
     fuss
    0.72
    Act Density 0.103%

    No Known Activations