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

    Neuronpedia

    INDEX
    Explanations

    phrases related to arguments, conclusions, and reasoning

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing conclusions, assumptions, or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abouts
    -0.68
    worth
    -0.64
    gie
    -0.62
    Exit
    -0.62
    inventoryQuantity
    -0.59
    apeake
    -0.59
    ciating
    -0.58
    elight
    -0.57
     Pastebin
    -0.56
    nect
    -0.55
    POSITIVE LOGITS
     that
    1.25
     moreover
    1.09
    that
    1.07
     furthermore
    1.06
     therefore
    0.95
     however
    0.85
     convinc
    0.83
     emphatically
    0.79
     THAT
    0.79
     unequivocally
    0.76
    Act Density 0.435%

    No Known Activations