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

    Neuronpedia

    INDEX
    Explanations

    references to people and groups

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

    "Those" followed by relative pronouns or prepositions

    np_acts-logits-general · gemini-2.0-flash

    those followed by who or a group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     varandra
    -0.66
     rivista
    -0.65
     nuages
    -0.65
     lèvres
    -0.64
     pères
    -0.64
     prisonniers
    -0.59
     itſelf
    -0.59
     wikipagina
    -0.59
     cdti
    -0.57
    первых
    -0.57
    POSITIVE LOGITS
     who
    1.25
     pesky
    0.88
     involved
    0.87
     that
    0.85
     whose
    0.78
     same
    0.78
    genen
    0.76
     few
    0.75
     of
    0.74
     responsible
    0.72
    Act Density 0.080%

    No Known Activations