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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associations in the context of data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    httphttps
    -1.05
     itſelf
    -1.02
     Monfieur
    -0.95
     Houſe
    -0.93
     myſelf
    -0.90
     purpoſe
    -0.89
     houſe
    -0.86
    ImageContext
    -0.85
     whoſe
    -0.84
    ſelf
    -0.81
    POSITIVE LOGITS
    subsubsection
    0.47
    a
    0.35
    y
    0.32
     i
    0.32
     $\
    0.31
     
    0.31
    1
    0.30
    you
    0.29
    D
    0.29
     rata
    0.28
    Act Density 1.040%

    No Known Activations