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

    Neuronpedia

    INDEX
    Explanations

    phrases related to safety precautions

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation and patterns suggesting conclusion or completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     waged
    -0.70
     alleged
    -0.69
     compelled
    -0.67
     outraged
    -0.67
     inference
    -0.66
     unprecedented
    -0.66
     subsystem
    -0.66
     unrem
    -0.65
     satell
    -0.65
     sustained
    -0.65
    POSITIVE LOGITS
     Alternatively
    1.54
     Otherwise
    1.43
     Remember
    1.34
     Depending
    1.34
     Ideally
    1.34
     Lastly
    1.33
     Also
    1.31
     Additionally
    1.30
     However
    1.28
     Beware
    1.25
    Act Density 0.361%

    No Known Activations