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

    Neuronpedia

    INDEX
    Explanations

    references to interpersonal relationships and pronouns related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    759
    -0.17
     yourselves
    -0.17
    isci
    -0.15
    eno
    -0.15
    728
    -0.15
    ucc
    -0.15
    ModelProperty
    -0.14
    antino
    -0.14
    ĶĦ
    -0.14
    //{{
    -0.14
    POSITIVE LOGITS
    oken
    0.17
    /us
    0.17
    ek
    0.15
    ORN
    0.15
    pit
    0.14
    дÑĢом
    0.14
    VR
    0.14
    external
    0.14
    URES
    0.14
    usty
    0.13
    Act Density 0.275%

    No Known Activations