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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .selenium
    -0.17
    orna
    -0.16
    opak
    -0.14
     coz
    -0.14
    riend
    -0.14
    von
    -0.14
     medi
    -0.13
    happy
    -0.13
    uraa
    -0.13
    etter
    -0.13
    POSITIVE LOGITS
     itself
    0.16
     thirsty
    0.15
     tant
    0.15
    ixo
    0.15
    ohen
    0.15
    .done
    0.15
    PED
    0.14
     дело
    0.14
    -done
    0.14
    aken
    0.14
    Act Density 0.111%

    No Known Activations