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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and references associated with locations and data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahan
    -0.17
    elp
    -0.17
    ruh
    -0.16
    637
    -0.16
    hetto
    -0.16
    ServiceProvider
    -0.16
    chants
    -0.15
    ilde
    -0.15
     Cement
    -0.15
    forcer
    -0.15
    POSITIVE LOGITS
    batch
    0.16
    pra
    0.16
    дÑĥ
    0.15
    orph
    0.15
    ungi
    0.15
    anus
    0.15
     Vig
    0.14
    bench
    0.14
     stri
    0.14
    wed
    0.14
    Act Density 0.031%

    No Known Activations