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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recommendations and endorsements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ntax
    -0.15
    ادÙĩ
    -0.15
    _APB
    -0.14
    ãĤīãģĹ
    -0.14
    .mousePosition
    -0.13
    γÏģα
    -0.13
     retrospective
    -0.13
    ãģŁãģĹ
    -0.13
    edis
    -0.13
    axter
    -0.13
    POSITIVE LOGITS
     recommendation
    1.03
     recommendations
    0.99
     recommended
    0.91
     recommend
    0.91
    Recommend
    0.85
    recommend
    0.84
     Recommendations
    0.84
     Recommendation
    0.82
     recommends
    0.81
     Recommend
    0.79
    Act Density 0.019%

    No Known Activations