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

    Neuronpedia

    INDEX
    Explanations

    boolean values indicating configuration settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etag
    -0.16
    loth
    -0.15
    lor
    -0.14
    εÏĢ
    -0.14
    HasBeenSet
    -0.14
    eln
    -0.14
    ech
    -0.14
    OOM
    -0.14
    με
    -0.14
    dar
    -0.13
    POSITIVE LOGITS
    /false
    0.21
    addin
    0.15
    conomy
    0.15
    oppel
    0.15
    berman
    0.14
    syscall
    0.14
    åĿĤ
    0.14
    ushima
    0.14
    STALL
    0.14
    orton
    0.14
    Act Density 0.044%

    No Known Activations