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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of people

    oai_token-act-pair · gpt-3.5-turbo

    specific names and representations of artistic works or performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obi
    -0.87
    ipper
    -0.82
    Cub
    -0.82
    apo
    -0.81
    omez
    -0.80
    ippers
    -0.80
    aders
    -0.77
    orney
    -0.77
    Gb
    -0.76
    é»Ĵ
    -0.75
    POSITIVE LOGITS
     Sat
    1.64
     Stand
    1.49
     Sit
    1.43
    sat
    1.42
     sat
    1.40
     STAND
    1.36
    Sit
    1.34
     sit
    1.33
    Stand
    1.31
     stand
    1.30
    Act Density 0.239%

    No Known Activations