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

    Neuronpedia

    INDEX
    Explanations

    the letter "t" occurring at the end of words

    oai_token-act-pair · gpt-3.5-turbo

    contractions of the verb "to be," specifically focusing on negative forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.76
     Skydragon
    -0.73
     gorilla
    -0.71
    EStream
    -0.71
    nesota
    -0.70
     tremend
    -0.69
     intern
    -0.68
     behavi
    -0.67
    ĪĴ
    -0.65
     undermin
    -0.64
    POSITIVE LOGITS
    aken
    1.10
    ractor
    1.08
    asks
    1.04
    ween
    1.02
    olkien
    1.01
    akers
    1.00
    otally
    1.00
    aker
    1.00
    roph
    0.99
    rav
    0.99
    Act Density 0.114%

    No Known Activations