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

    Neuronpedia

    INDEX
    Explanations

    references to organizational or institutional safety regulations and standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Endpoint
    -0.17
    STALL
    -0.17
    afone
    -0.15
    SCRI
    -0.15
    kiye
    -0.15
    .scalablytyped
    -0.15
    entials
    -0.15
    öz
    -0.15
    adero
    -0.15
    ãĥ¼ãĤº
    -0.15
    POSITIVE LOGITS
    o
    0.22
    ough
    0.17
    rax
    0.16
    atra
    0.16
    l
    0.15
    c
    0.15
     ch
    0.15
    cies
    0.15
     giant
    0.15
    cio
    0.15
    Act Density 0.051%

    No Known Activations