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

    Neuronpedia

    INDEX
    Explanations

    articles that signify importance or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quam
    -0.19
    comes
    -0.15
    rone
    -0.15
    zek
    -0.14
    .ibm
    -0.14
    uen
    -0.14
    opia
    -0.14
     Nile
    -0.14
    .sponge
    -0.13
    bone
    -0.13
    POSITIVE LOGITS
     portion
    0.16
    енÑģ
    0.16
     addCriterion
    0.14
    ection
    0.14
    /Dk
    0.14
    dee
    0.14
    Rx
    0.14
    лада
    0.13
    istar
    0.13
    ivant
    0.13
    Act Density 0.136%

    No Known Activations