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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their associated verbs, reflecting personal perspectives and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    571
    -0.18
    entar
    -0.17
    ixin
    -0.16
    claimer
    -0.15
    onta
    -0.15
    outh
    -0.15
    erve
    -0.15
    iko
    -0.14
    athing
    -0.14
    оÑĢом
    -0.14
    POSITIVE LOGITS
    pmat
    0.15
    ISIBLE
    0.15
     wonder
    0.15
     Cheng
    0.15
    ä¼ı
    0.14
    okino
    0.14
     WINAPI
    0.14
    adr
    0.14
    aleigh
    0.14
    ihanna
    0.14
    Act Density 0.303%

    No Known Activations