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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and expressions of self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CHANT
    -0.15
     punt
    -0.15
    ód
    -0.15
     Böl
    -0.15
    atem
    -0.14
    á»IJ
    -0.14
    ATEGORIES
    -0.14
    udget
    -0.14
    athe
    -0.14
    .intellij
    -0.14
    POSITIVE LOGITS
    oen
    0.18
    aign
    0.15
    ingular
    0.15
    -angular
    0.14
    ÙĪØŃ
    0.14
    رÙĪج
    0.14
    acs
    0.14
    igate
    0.13
    usp
    0.13
    opsy
    0.13
    Act Density 0.076%

    No Known Activations