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

    Neuronpedia

    INDEX
    Explanations

    technical language related to mathematics and statistics, particularly focused on equations and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <?
    -0.56
    typename
    -0.54
    ος
    -0.52
    AxisAlignment
    -0.51
    loz
    -0.51
    actus
    -0.50
    ושים
    -0.49
    にかけて
    -0.48
    ̍t
    -0.48
    ResponseBody
    -0.48
    POSITIVE LOGITS
     compare
    1.15
    compare
    1.11
     comparison
    1.11
     compared
    1.09
    Compare
    1.09
     Compare
    1.07
     compares
    1.06
     comparing
    1.02
     Comparison
    1.01
    Comparison
    1.00
    Act Density 0.989%

    No Known Activations