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

    Neuronpedia

    INDEX
    Explanations

    clauses and phrases that imply conditionality or specification

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

    "That" followed by "is"

    np_acts-logits-general · gemini-2.0-flash

    relative clauses using that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lında
    -0.41
     newName
    -0.41
     rollen
    -0.40
     biela
    -0.40
     disponibilité
    -0.40
     plegable
    -0.40
     przedmio
    -0.39
    seamnă
    -0.39
     imprensa
    -0.38
     depositphotos
    -0.38
    POSITIVE LOGITS
     which
    0.58
    which
    0.58
     whose
    0.57
     والتي
    0.57
    whose
    0.56
     jonka
    0.56
    verifyException
    0.56
     joka
    0.53
     والذي
    0.53
     שאי
    0.52
    Act Density 0.368%

    No Known Activations