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

    Neuronpedia

    INDEX
    Explanations

    references to evidence-based practices and research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quist
    -0.16
    éĻIJ
    -0.15
    plevel
    -0.15
    inz
    -0.14
    stad
    -0.14
    bone
    -0.14
    ÙĪØ·
    -0.14
    /email
    -0.14
    iling
    -0.14
    egade
    -0.14
    POSITIVE LOGITS
    -based
    0.19
    ropa
    0.18
    -base
    0.18
     tam
    0.18
    abase
    0.16
    eum
    0.16
     base
    0.16
    uality
    0.16
     gathering
    0.16
     gì
    0.16
    Act Density 0.026%

    No Known Activations