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

    Neuronpedia

    INDEX
    Explanations

    references to specific groups of people or entities

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

    "those" followed by a preposition or relative pronoun

    np_acts-logits-general · gemini-2.0-flash

    those who or that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lehr
    -0.42
    isEdit
    -0.41
    edit
    -0.38
    EDIT
    -0.38
    editar
    -0.37
     iconFacebook
    -0.37
    uvw
    -0.36
    neat
    -0.36
     maire
    -0.36
    isValid
    -0.36
    POSITIVE LOGITS
     those
    1.17
     Those
    1.05
     THOSE
    1.04
    those
    1.02
    Those
    1.00
     ceux
    0.96
    queles
    0.91
     aquellos
    0.89
    那些
    0.87
     who
    0.85
    Act Density 0.117%

    No Known Activations