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

    Neuronpedia

    INDEX
    Explanations

    references to Greek culture and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    readcr
    -0.16
    cce
    -0.16
    icity
    -0.16
    ÑģÑĮ
    -0.15
    ization
    -0.15
    c
    -0.15
    cle
    -0.15
    oooooooo
    -0.15
    truth
    -0.15
    riers
    -0.15
    POSITIVE LOGITS
    iness
    0.23
    stakes
    0.22
    zeitig
    0.21
    fulness
    0.20
    ening
    0.20
    ened
    0.19
    orative
    0.19
    fully
    0.18
    -quarters
    0.18
    quarters
    0.17
    Act Density 0.078%

    No Known Activations