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

    Neuronpedia

    INDEX
    Explanations

    phrases requesting additional information or clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovic
    -0.15
    adele
    -0.15
    izzle
    -0.15
    usto
    -0.14
    izer
    -0.14
    iazza
    -0.14
    /body
    -0.14
    ourage
    -0.13
    endale
    -0.13
    åĩĮ
    -0.13
    POSITIVE LOGITS
     details
    0.29
     information
    0.29
     detail
    0.28
     background
    0.26
     specifics
    0.23
     facts
    0.22
    information
    0.21
     info
    0.21
     ways
    0.20
     about
    0.20
    Act Density 0.017%

    No Known Activations