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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "edit" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullo
    -0.16
    Neill
    -0.15
     Khan
    -0.14
    jd
    -0.14
     Peters
    -0.14
    keley
    -0.14
    anzi
    -0.14
    ãĤĵ
    -0.14
    æĨ
    -0.14
    ibi
    -0.14
    POSITIVE LOGITS
    ERENCE
    0.17
    ehr
    0.17
    .tree
    0.16
    akest
    0.15
    æ¤į
    0.15
    æŃ©
    0.14
    523
    0.14
    atorio
    0.14
    izzer
    0.14
     rem
    0.14
    Act Density 0.002%

    No Known Activations