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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases that advise against certain actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onde
    -0.15
     neutral
    -0.15
    ücken
    -0.14
    .EventArgs
    -0.14
     Neutral
    -0.14
    ären
    -0.14
     neutr
    -0.14
    aira
    -0.14
     Peyton
    -0.13
    ün
    -0.13
    POSITIVE LOGITS
    ستÙĩ
    0.17
    침
    0.15
    ofi
    0.15
    _BINDING
    0.14
    oice
    0.14
    enta
    0.14
    mind
    0.14
    .setViewport
    0.14
     Card
    0.14
     use
    0.14
    Act Density 0.080%

    No Known Activations