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

    Neuronpedia

    INDEX
    Explanations

    HTML tags for formatting and links

    oai_token-act-pair · gpt-3.5-turbo

    HTML or XML closing tags and related syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     poop
    -0.54
     freezing
    -0.53
     Dexter
    -0.53
     deficient
    -0.53
     centres
    -0.53
     proof
    -0.51
     constantly
    -0.51
     Bun
    -0.51
     whiff
    -0.51
     Bay
    -0.50
    POSITIVE LOGITS
     </
    4.05
    )</
    2.96
    </
    2.82
    .</
    2.80
     <
    1.80
     <!--
    1.78
    ></
    1.74
     [/
    1.65
    "></
    1.64
    .<
    1.62
    Act Density 0.009%

    No Known Activations