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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and terms related to self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     má»Ŀi
    -0.16
    istrovstvÃŃ
    -0.15
    enu
    -0.15
    ama
    -0.15
    à¤Ķ
    -0.15
    nable
    -0.15
    levance
    -0.14
    tright
    -0.14
    اÛĮÙĩ
    -0.14
    LOOR
    -0.14
    POSITIVE LOGITS
    iam
    0.17
    ActionCreators
    0.16
     Madness
    0.15
    leine
    0.15
    achuset
    0.14
    owo
    0.14
    ëįĶëĭĪ
    0.14
    945
    0.14
    ican
    0.14
    ย
    0.14
    Act Density 0.001%

    No Known Activations