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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or names in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yonel
    -0.27
    eler
    -0.20
    els
    -0.19
    ell
    -0.19
    elle
    -0.19
    ess
    -0.18
    ex
    -0.18
    el
    -0.18
    em
    -0.18
    else
    -0.18
    POSITIVE LOGITS
    abyrinth
    0.24
    ifestyles
    0.23
    ateral
    0.23
    iferay
    0.23
    abyrin
    0.22
    uggage
    0.20
    AYOUT
    0.20
    ITERAL
    0.20
    apsed
    0.19
    orraine
    0.19
    Act Density 2.008%

    No Known Activations