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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eno
    -0.69
    verage
    -0.69
    AMI
    -0.65
    tumblr
    -0.64
    thood
    -0.64
    orate
    -0.62
    />
    -0.60
    ional
    -0.60
    IRO
    -0.59
     onwards
    -0.59
    POSITIVE LOGITS
     oldest
    1.14
     latter
    1.08
     youngest
    1.05
     largest
    1.02
     biggest
    1.02
     longest
    1.01
     fastest
    0.96
     smallest
    0.96
     strongest
    0.95
     newest
    0.93
    Act Density 0.138%

    No Known Activations