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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "caps" appearing in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to sports teams or their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Heist
    -0.78
    issance
    -0.70
     Galile
    -0.69
    Iraq
    -0.69
    Ô
    -0.68
    Bey
    -0.66
     Sheen
    -0.63
    ;;;;;;;;;;;;
    -0.63
     obj
    -0.62
    Marie
    -0.62
    POSITIVE LOGITS
    icum
    1.27
    ules
    1.25
    aic
    1.15
    itol
    1.07
    itals
    1.06
    ule
    1.04
    mith
    1.01
    acus
    0.99
     caps
    0.96
    uits
    0.96
    Act Density 0.015%

    No Known Activations