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

    Neuronpedia

    INDEX
    Explanations

    special characters and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ••••
    -0.83
     <
    -0.75
     Tre
    -0.74
     in
    -0.74
     Rosenthal
    -0.73
    aderie
    -0.72
    homonymie
    -0.70
     Chand
    -0.70
     Mek
    -0.70
     E
    -0.69
    POSITIVE LOGITS
     Efq
    1.20
     Theſe
    1.14
     themſelves
    1.14
     doubtnut
    1.09
     photolibrary
    1.08
     itſelf
    1.05
     crdi
    1.03
    rzez
    1.03
     ainfi
    1.02
     Monfieur
    1.01
    Act Density 1.054%

    No Known Activations