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

    Neuronpedia

    INDEX
    Explanations

    references to technology-related issues and concerns within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acter
    -0.15
     crippling
    -0.15
     acompan
    -0.15
     ayr
    -0.14
    ierce
    -0.14
    ville
    -0.14
    shelf
    -0.14
    ccione
    -0.14
     иÑģÑħод
    -0.14
    ACTER
    -0.13
    POSITIVE LOGITS
     po
    0.15
     Kafka
    0.15
    ç³
    0.15
     Hor
    0.15
    urf
    0.14
     patch
    0.14
     Ade
    0.14
     suff
    0.14
     basic
    0.14
     neglected
    0.14
    Act Density 0.403%

    No Known Activations