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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "exact."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     I
    -0.54
     
    -0.51
     a
    -0.49
    ↵↵
    -0.49
     En
    -0.48
     p
    -0.47
    pecting
    -0.47
     kid
    -0.47
     For
    -0.46
     et
    -0.46
    POSITIVE LOGITS
     itſelf
    1.21
     myſelf
    1.02
     himſelf
    1.00
    </thead>
    0.99
     Jefus
    0.98
     pleaſure
    0.97
     Efq
    0.97
     Roskov
    0.94
     themſelves
    0.92
    EndProject
    0.92
    Act Density 0.114%

    No Known Activations