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

    Neuronpedia

    INDEX
    Explanations

    periods at the end of sentences

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

    figure references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tershire
    -0.68
     myſelf
    -0.64
     Normdatei
    -0.60
    colgante
    -0.59
     poffe
    -0.59
    mpagne
    -0.58
     deſt
    -0.57
     tranſ
    -0.56
    ElementException
    -0.56
     raiſ
    -0.55
    POSITIVE LOGITS
    <bos>
    0.53
    .
    0.46
    ).
    0.36
    Bài
    0.36
    Figure
    0.35
    reszcie
    0.34
     Abbildung
    0.34
    》.
    0.34
    .)
    0.33
     Figure
    0.33
    Act Density 0.049%

    No Known Activations