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

    Neuronpedia

    INDEX
    Explanations

    terms related to prevention and minimizing issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emi
    -0.15
    linger
    -0.14
    ikit
    -0.13
    rottle
    -0.13
    mys
    -0.13
    idden
    -0.13
    anz
    -0.13
    éļľ
    -0.13
    çħ§
    -0.13
    verb
    -0.13
    POSITIVE LOGITS
     artifacts
    0.23
     arte
    0.20
     ghost
    0.20
     premature
    0.20
     artifact
    0.20
     sag
    0.19
     Sag
    0.19
    ifacts
    0.18
     vign
    0.18
    artifact
    0.17
    Act Density 0.285%

    No Known Activations