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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and language reflecting self-reference

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

    self and ownership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     y
    -0.39
     Ches
    -0.39
     sp
    -0.39
     proto
    -0.37
     All
    -0.36
     ze
    -0.36
     pleaded
    -0.36
     ci
    -0.36
     region
    -0.35
     Dream
    -0.35
    POSITIVE LOGITS
    évaluateur
    0.80
    parsedMessage
    0.75
    rungsseite
    0.73
    OGND
    0.69
    RTEX
    0.69
    WriteTagHelper
    0.69
    verwijspagina
    0.67
     '\\;'
    0.66
    ftagPool
    0.64
    ſelf
    0.63
    Act Density 0.054%

    No Known Activations