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

    Neuronpedia

    INDEX
    Explanations

    elements and syntax used in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favor
    -0.15
     favour
    -0.15
     Miller
    -0.15
     Reese
    -0.15
    ulumi
    -0.14
     defer
    -0.14
     Kings
    -0.14
    iana
    -0.14
    hatt
    -0.14
     Gilbert
    -0.14
    POSITIVE LOGITS
    ANJI
    0.17
    ornings
    0.17
    ERRU
    0.16
    .www
    0.15
    ARAM
    0.15
    åĴ²
    0.15
    otron
    0.15
    \Migrations
    0.15
    751
    0.14
     Grill
    0.14
    Act Density 0.008%

    No Known Activations