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

    Neuronpedia

    INDEX
    Explanations

    occurrences of high-frequency pronouns and verbs conveying actions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     having
    -0.19
    znik
    -0.17
    having
    -0.16
    одо
    -0.16
     Having
    -0.15
    ogg
    -0.14
    à¸ĺ
    -0.14
    ipi
    -0.14
    Having
    -0.14
    RTC
    -0.13
    POSITIVE LOGITS
    ATTERN
    0.15
    Gift
    0.15
    PropTypes
    0.15
    vat
    0.15
     ped
    0.15
     slun
    0.14
    emie
    0.14
     slur
    0.14
    lify
    0.14
    chie
    0.14
    Act Density 0.018%

    No Known Activations