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

    Neuronpedia

    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "com."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sweep
    -0.75
     affirm
    -0.74
     blush
    -0.74
     unheard
    -0.72
     thrill
    -0.70
     authentic
    -0.70
     tampering
    -0.69
     clinch
    -0.68
     utter
    -0.66
     intercept
    -0.66
    POSITIVE LOGITS
    nz
    1.07
     Accessed
    0.94
    uploads
    0.89
    wordpress
    0.87
    au
    0.86
    facebook
    0.84
    icio
    0.83
     Retrieved
    0.82
    cn
    0.82
    ca
    0.81
    Act Density 0.063%

    No Known Activations