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

    Neuronpedia

    INDEX
    Explanations

    strings related to digital forms of user data or identity attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -2.41
     myſelf
    -2.38
     ―――――
    -2.29
     ſeveral
    -2.01
     themſelves
    -2.00
     Theſe
    -2.00
    ſelf
    -1.98
     Jefus
    -1.96
     becauſe
    -1.95
     himſelf
    -1.95
    POSITIVE LOGITS
     '
    2.96
     ‘
    2.55
    ('
    2.11
     ('
    1.87
    ‘
    1.82
     ['
    1.59
     ’
    1.59
    ='
    1.59
     `
    1.54
     "
    1.54
    Act Density 0.053%

    No Known Activations