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

    Neuronpedia

    INDEX
    Explanations

    links to external websites

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conclud
    -0.72
     laborers
    -0.70
     handwriting
    -0.69
    Ļ½
    -0.68
    ãĥĥãĥī
    -0.68
     distilled
    -0.65
     induct
    -0.65
    ħĭ
    -0.64
    ãĥ¼ãĥĨ
    -0.63
     monkeys
    -0.63
    POSITIVE LOGITS
    esp
    0.98
    facebook
    0.98
    twitter
    0.96
    gov
    0.91
    nz
    0.91
    imgur
    0.90
    github
    0.90
    polit
    0.83
    assetsadobe
    0.83
    debian
    0.82
    Act Density 0.014%

    No Known Activations