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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating continuity or past actions related to processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.18
    ngen
    -0.16
    /from
    -0.14
    ns
    -0.13
    /of
    -0.13
    ungan
    -0.13
     aka
    -0.13
    æĥij
    -0.13
    isted
    -0.12
    aways
    -0.12
    POSITIVE LOGITS
     же
    0.27
     ìĿ´ëĬĶ
    0.18
    istrovstvÃŃ
    0.17
     ìĿ´ëŁ¬íķľ
    0.15
     wiÄĻc
    0.15
     cela
    0.15
    Ñĩем
    0.14
    ,this
    0.14
     this
    0.14
    >this
    0.14
    Act Density 0.446%

    No Known Activations