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

    Neuronpedia

    INDEX
    Explanations

    statements asserting factual information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thus
    -0.15
    ensis
    -0.15
    jac
    -0.14
    nek
    -0.14
    foundland
    -0.14
    ould
    -0.14
    ULD
    -0.13
    αιν
    -0.13
    /package
    -0.13
    acht
    -0.13
    POSITIVE LOGITS
     fact
    0.23
    itious
    0.23
    uality
    0.18
    ually
    0.18
    977
    0.15
    ease
    0.14
    fact
    0.14
    éo
    0.14
    TA
    0.14
    arding
    0.13
    Act Density 0.034%

    No Known Activations