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

    Neuronpedia

    INDEX
    Explanations

    phrases related to permissions and intellectual property rights

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

    "these" or "those" as demonstrative pronouns

    np_acts-logits-general · gemini-2.0-flash

    those things or these things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __":
    -0.55
    TagMode
    -0.48
    //
    -0.47
    WebElementEntity
    -0.46
    çage
    -0.45
    <bos>
    -0.45
     two
    -0.45
     />";
    -0.44
     MainAxisSize
    -0.44
    DataContract
    -0.43
    POSITIVE LOGITS
     these
    1.97
    these
    1.77
    これらの
    1.73
    These
    1.58
     These
    1.57
    這些
    1.52
     THESE
    1.50
    这些
    1.50
     desses
    1.29
     thefe
    1.28
    Act Density 0.853%

    No Known Activations