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

    Neuronpedia

    INDEX
    Explanations

    language that emphasizes precision and specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ony
    -0.19
    ingen
    -0.15
    ani
    -0.15
    hunt
    -0.15
     mere
    -0.15
    ร
    -0.15
    anne
    -0.15
    hol
    -0.14
    istrovstvÃŃ
    -0.14
    anche
    -0.14
    POSITIVE LOGITS
    ities
    0.20
    -purpose
    0.20
    ially
    0.19
    ally
    0.17
    idades
    0.16
    ÑĮ
    0.16
     sayıda
    0.16
    ummings
    0.15
    ÑĪе
    0.15
    ̧
    0.15
    Act Density 0.033%

    No Known Activations