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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks at the end of sentences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     councill
    -0.76
     independ
    -0.74
    »Ĵ
    -0.72
     perspect
    -0.71
     mosqu
    -0.68
     volunte
    -0.68
     acquaintance
    -0.66
     unden
    -0.63
     metic
    -0.63
     exha
    -0.62
    POSITIVE LOGITS
     SHARES
    0.80
     Thumbnails
    0.80
     Emails
    0.75
     Looks
    0.70
     Shares
    0.69
     Updates
    0.69
    hran
    0.68
     Beware
    0.67
     Unable
    0.67
     ARTICLE
    0.66
    Act Density 0.016%

    No Known Activations