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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating participation or engagement in activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cassidy
    -0.17
    æ®
    -0.15
    aux
    -0.15
    pur
    -0.15
     Tobias
    -0.15
     ani
    -0.14
     shade
    -0.14
    ç°
    -0.13
     permutation
    -0.13
    tml
    -0.13
    POSITIVE LOGITS
    orable
    0.16
     Dez
    0.16
    ula
    0.16
     æĪ
    0.15
    uali
    0.15
    aed
    0.14
     Owners
    0.14
    ropdown
    0.14
     Right
    0.14
    ibase
    0.14
    Act Density 0.015%

    No Known Activations