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

    Neuronpedia

    INDEX
    Explanations

    terms related to names and their meanings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.16
     myſelf
    -1.08
     themſelves
    -1.00
     himſelf
    -0.99
     houſe
    -0.95
     ་་
    -0.90
     Houſe
    -0.89
     ſeveral
    -0.89
     uſed
    -0.87
     ſtand
    -0.87
    POSITIVE LOGITS
     lenker
    0.48
     reg
    0.45
    <h4>
    0.45
    STREAM
    0.43
     Mora
    0.43
     auto
    0.43
     ק
    0.42
     "
    0.42
     trụ
    0.41
     fra
    0.41
    Act Density 0.308%

    No Known Activations