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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emphasizing or drawing special attention to specific content

    oai_token-act-pair · gpt-3.5-turbo

    recurring punctuation marks and special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Paso
    -0.70
    senal
    -0.67
     Borders
    -0.66
     Slug
    -0.64
    eca
    -0.63
    aukee
    -0.59
     Folder
    -0.58
     Dragons
    -0.57
     Colomb
    -0.56
    Mob
    -0.56
    POSITIVE LOGITS
     gasp
    1.25
    albeit
    1.15
    again
    1.13
    perhaps
    1.08
    almost
    1.01
    fortunately
    1.00
    quite
    1.00
    surprisingly
    1.00
    according
    0.99
    literally
    0.98
    Act Density 0.107%

    No Known Activations