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

    Neuronpedia

    INDEX
    Explanations

    discussion of personal experiences and reflections

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

    Comes after the end of a paragraph

    np_acts-logits-general · gemini-2.0-flash

    lately or sometimes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    と思いました
    -0.59
     was
    -0.59
     fanns
    -0.55
     mogelijk
    -0.49
     WAS
    -0.48
     posibles
    -0.48
     mógł
    -0.47
     were
    -0.47
     looked
    -0.47
    ****************
    -0.46
    POSITIVE LOGITS
     sometimes
    1.46
     Occasionally
    1.45
     lately
    1.43
    Occasionally
    1.42
     occasionally
    1.38
    sometimes
    1.34
     Lately
    1.30
     Sometimes
    1.29
    Sometimes
    1.29
     kadang
    1.18
    Act Density 0.229%

    No Known Activations