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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety measures and precautions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nbsp
    -0.16
    visa
    -0.15
    inders
    -0.15
    alli
    -0.15
    ικο
    -0.15
    shaw
    -0.14
    Ù
    -0.14
    ners
    -0.14
    èĥŀ
    -0.14
    ource
    -0.14
    POSITIVE LOGITS
    .sb
    0.17
    ists
    0.16
    osi
    0.15
     Hubb
    0.15
    ify
    0.15
    ania
    0.15
    363
    0.14
    stalk
    0.14
    ANGLES
    0.14
    294
    0.14
    Act Density 0.033%

    No Known Activations