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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of written works like articles, books, treaties, bills, and series

    oai_token-act-pair · gpt-3.5-turbo

    references to events, articles, and various significant entities or subjects within contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dden
    -0.67
    Unknown
    -0.60
    fal
    -0.59
     Wrong
    -0.59
    Redd
    -0.58
    hend
    -0.58
    sbm
    -0.58
    ZI
    -0.57
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.56
    Weak
    -0.56
    POSITIVE LOGITS
     consisted
    1.21
     consists
    1.20
     comprises
    1.09
     revolves
    1.08
     reportedly
    0.99
     debuted
    0.98
     includes
    0.95
     operates
    0.94
     lasted
    0.93
     contains
    0.92
    Act Density 0.335%

    No Known Activations