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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "NEW" in the context of announcements or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    683
    -0.15
    ousse
    -0.14
    273
    -0.14
    &e
    -0.13
    KEN
    -0.13
     &
    -0.13
    hari
    -0.13
    este
    -0.13
     tracer
    -0.13
    SED
    -0.13
    POSITIVE LOGITS
     ilma
    0.16
    rror
    0.15
    eding
    0.15
    isol
    0.15
    ↵↵
    0.14
    ium
    0.14
    pit
    0.14
    ifest
    0.14
    aits
    0.14
    ittal
    0.14
    Act Density 0.000%

    No Known Activations