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

    Neuronpedia

    INDEX
    Explanations

    instances of escape characters in text or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.13
    دانشنامهٔ
    -1.09
     Theſe
    -1.05
     itſelf
    -1.04
     Monfieur
    -1.04
    wiſe
    -1.00
     ―――――
    -0.97
     ſeveral
    -0.96
     themſelves
    -0.94
     Kości
    -0.94
    POSITIVE LOGITS
    "\
    1.11
     \
    1.08
    :\
    1.05
     "\
    1.04
     "..\..\..\
    0.99
     '\
    0.98
    '\
    0.95
    .\
    0.94
     (\
    0.93
    (\
    0.90
    Act Density 0.415%

    No Known Activations