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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themselves
    -0.19
     Higgins
    -0.17
    694
    -0.15
     cerr
    -0.15
    ology
    -0.14
    hn
    -0.14
    abe
    -0.14
    hta
    -0.14
    ç±į
    -0.14
     it
    -0.14
    POSITIVE LOGITS
     raining
    0.26
    edn
    0.18
    iner
    0.18
     incumbent
    0.17
     CActive
    0.17
    SAN
    0.17
     -*-č↵
    0.16
    chy
    0.16
    rain
    0.16
    alic
    0.16
    Act Density 0.214%

    No Known Activations