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

    Neuronpedia

    INDEX
    Explanations

    references to research findings and conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Punctuation followed by "future/implications"

    np_acts-logits-general · gemini-2.0-flash

    future implications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hauptartikel
    -0.79
    IntoConstraints
    -0.72
    HtmlAttribute
    -0.68
    ensement
    -0.62
    Chham
    -0.58
    Попис
    -0.58
    锈钢
    -0.57
     Contoh
    -0.54
     configurer
    -0.54
     LUMP
    -0.53
    POSITIVE LOGITS
     future
    1.23
     Future
    1.16
    Future
    1.13
    future
    1.10
    FUTURE
    0.91
     FUTURE
    0.90
     implications
    0.82
    未来的
    0.81
     Implications
    0.81
     futuro
    0.77
    Act Density 0.598%

    No Known Activations