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

    Neuronpedia

    INDEX
    Explanations

    contractions containing an apostrophe followed by a word

    oai_token-act-pair · gpt-3.5-turbo

    instances of the apostrophe character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swer
    -0.67
    ħĭ
    -0.64
     peanuts
    -0.64
     spar
    -0.63
    sted
    -0.63
     stacks
    -0.63
     Transfer
    -0.62
     quizz
    -0.62
     slic
    -0.61
    nown
    -0.61
    POSITIVE LOGITS
    avez
    0.84
    Ag
    0.82
    hom
    0.80
    Aut
    0.80
    Allah
    0.79
    orange
    0.78
    esp
    0.77
    Est
    0.75
    eros
    0.75
    Angelo
    0.74
    Act Density 0.018%

    No Known Activations