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

    Neuronpedia

    INDEX
    Explanations

    words that indicate particular details or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mere
    -0.18
    iesel
    -0.17
    anja
    -0.17
    stead
    -0.16
    weit
    -0.16
    cn
    -0.16
    okit
    -0.15
     majority
    -0.14
    anche
    -0.14
    ร
    -0.14
    POSITIVE LOGITS
     biá»ĩt
    0.20
    -purpose
    0.20
    ulty
    0.18
    ially
    0.17
    ities
    0.16
    ">//
    0.16
    TOTYPE
    0.15
    blr
    0.14
    ırak
    0.14
     sayıda
    0.14
    Act Density 0.037%

    No Known Activations