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

    Neuronpedia

    INDEX
    Explanations

    terms related to trouble or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    strstr
    -0.15
    lint
    -0.15
    trash
    -0.15
    conde
    -0.15
    iddled
    -0.15
    мага
    -0.14
    ror
    -0.14
    isz
    -0.14
    åŀ
    -0.14
    POSITIVE LOGITS
    514
    0.17
    Rated
    0.15
    ãģª
    0.15
    /mock
    0.14
    chwitz
    0.13
    utom
    0.13
    orraine
    0.13
    especially
    0.13
     inoc
    0.13
     edge
    0.13
    Act Density 0.049%

    No Known Activations