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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate technical specifications or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     concession
    -0.16
    gran
    -0.16
     Foo
    -0.15
    zet
    -0.15
    coder
    -0.15
    medi
    -0.14
     medi
    -0.13
    enheim
    -0.13
    verity
    -0.13
    rze
    -0.13
    POSITIVE LOGITS
    asmus
    0.16
    pell
    0.15
    798
    0.15
    byss
    0.15
    etz
    0.14
    ebra
    0.14
    æĬŀ
    0.14
    chw
    0.14
    akest
    0.14
    uddy
    0.14
    Act Density 0.001%

    No Known Activations