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

    Neuronpedia

    INDEX
    Explanations

    the word "specific" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ร
    -0.17
    our
    -0.16
    ekler
    -0.15
    hood
    -0.15
    orous
    -0.14
    yll
    -0.14
    ony
    -0.14
    hra
    -0.14
     Holmes
    -0.14
    ipo
    -0.13
    POSITIVE LOGITS
    ities
    0.30
    ally
    0.25
    ially
    0.24
    ity
    0.24
    -purpose
    0.23
    ALLY
    0.22
    /general
    0.19
    ITY
    0.17
    ITIES
    0.16
    ités
    0.16
    Act Density 0.037%

    No Known Activations