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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms and symbols, particularly those related to probability and distributions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistical concepts and mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gered
    -0.69
    geries
    -0.65
    iliated
    -0.64
     spills
    -0.62
    gery
    -0.62
     rolls
    -0.61
     pilgrimage
    -0.61
     Rost
    -0.60
     advancement
    -0.60
     sabotage
    -0.60
    POSITIVE LOGITS
    {\
    1.16
     {\
    1.04
    }\
    1.02
    {
    1.02
    \)
    1.01
    \
    0.98
    align
    0.98
    _{
    0.95
    ²
    0.89
    }
    0.87
    Act Density 0.065%

    No Known Activations