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

    Neuronpedia

    INDEX
    Explanations

    statements regarding the nature of knowledge or truth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alc
    -0.16
    uber
    -0.15
    riad
    -0.14
    alah
    -0.14
    Indexes
    -0.14
    inka
    -0.14
    kw
    -0.14
    alt
    -0.14
    af
    -0.14
    rf
    -0.14
    POSITIVE LOGITS
    quired
    0.15
    mpar
    0.14
    oggler
    0.14
     STDCALL
    0.14
    maz
    0.13
    achs
    0.13
    òi
    0.13
    ocol
    0.13
    .twimg
    0.13
    ηÏĤ
    0.13
    Act Density 0.043%

    No Known Activations