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

    Neuronpedia

    INDEX
    Explanations

    legal disclaimers and information related to copyright and permissions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surely
    -0.66
     anew
    -0.66
    Ò
    -0.65
    eno
    -0.65
    chant
    -0.64
    cha
    -0.63
     Suddenly
    -0.62
    abuse
    -0.62
    factor
    -0.62
    ÙĴ
    -0.62
    POSITIVE LOGITS
     contents
    1.24
     opinions
    1.23
     foregoing
    1.14
     following
    1.10
     author
    1.06
     views
    1.04
     above
    1.01
     content
    0.98
     links
    0.97
    ses
    0.97
    Act Density 0.310%

    No Known Activations