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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-3.5-turbo

    statistical terminology related to distributions and probability functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sammy
    -0.72
    rency
    -0.69
     Watkins
    -0.68
     jog
    -0.64
    gered
    -0.64
    arcity
    -0.64
     Samar
    -0.64
     clinch
    -0.63
     conduc
    -0.62
     hugging
    -0.62
    POSITIVE LOGITS
    \
    1.02
    \.
    0.85
    notice
    0.85
    __
    0.84
    actionDate
    0.83
    \)
    0.83
    _{
    0.82
    {
    0.81
    Dir
    0.79
    {\
    0.79
    Act Density 0.038%

    No Known Activations