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

    Neuronpedia

    INDEX
    Explanations

    concepts related to ongoing social and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trusts
    -0.14
    .Companion
    -0.14
     indem
    -0.14
    DELAY
    -0.14
    ypass
    -0.14
    asad
    -0.14
    RLF
    -0.13
    ATAB
    -0.13
    -touch
    -0.13
    .bio
    -0.13
    POSITIVE LOGITS
    idia
    0.17
     cerr
    0.15
    edir
    0.15
    esin
    0.14
    avl
    0.14
    strup
    0.14
     Ket
    0.13
    YE
    0.13
     barrel
    0.13
     another
    0.13
    Act Density 0.634%

    No Known Activations