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

    Neuronpedia

    INDEX
    Explanations

    references to tags and their importance in text

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

    "Tag" or "tagged" followed by another word

    np_acts-logits-general · gemini-2.0-flash

    tag archives or tagged entries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تانيه
    -0.74
    exprimer
    -0.72
    wright
    -0.71
     Illustrations
    -0.66
    mpy
    -0.65
    
    -0.65
    Inhoud
    -0.60
    ristiano
    -0.59
     Reverso
    -0.59
    ']));
    -0.59
    POSITIVE LOGITS
     tag
    1.66
     tags
    1.66
     Tag
    1.57
    tags
    1.44
     TAG
    1.44
     Tags
    1.44
    Tag
    1.39
    WithTag
    1.29
     tagging
    1.26
    Tags
    1.25
    Act Density 0.118%

    No Known Activations