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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant amounts or concepts related to measurement and comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bel
    -0.15
    вод
    -0.15
    ERRU
    -0.15
    itals
    -0.15
    472
    -0.14
    ilig
    -0.14
    ysz
    -0.14
     Dorm
    -0.14
    .bel
    -0.14
     suspend
    -0.14
    POSITIVE LOGITS
    /topics
    0.15
    rollo
    0.15
    oten
    0.15
    izable
    0.15
    iza
    0.14
    .codehaus
    0.14
    uler
    0.14
    otate
    0.14
    izer
    0.14
    aliz
    0.13
    Act Density 0.123%

    No Known Activations