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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with the punctuation mark "."

    oai_token-act-pair · gpt-3.5-turbo

    instances of sentences or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     extinguished
    -0.79
     restraint
    -0.77
     overt
    -0.75
     extingu
    -0.75
     barric
    -0.71
     grip
    -0.71
     involuntary
    -0.70
     reflex
    -0.70
     sacked
    -0.69
     angle
    -0.69
    POSITIVE LOGITS
     Lastly
    1.64
     Additionally
    1.54
     Finally
    1.38
     Needless
    1.36
     Hopefully
    1.30
     Overall
    1.26
     Furthermore
    1.24
    Lastly
    1.22
     Unfortunately
    1.21
     Ultimately
    1.20
    Act Density 0.512%

    No Known Activations