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

    Neuronpedia

    INDEX
    Explanations

    instances of structured social interactions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rup
    -0.15
    rych
    -0.14
    asl
    -0.14
    LETE
    -0.13
    aset
    -0.13
     bump
    -0.13
     Spar
    -0.13
    chts
    -0.13
    alo
    -0.13
    usat
    -0.13
    POSITIVE LOGITS
     itself
    0.17
     stesso
    0.17
    jeta
    0.15
    ird
    0.14
    ogr
    0.13
     themselves
    0.13
     нанеÑģ
    0.13
     же
    0.13
    quia
    0.13
    ä¿
    0.13
    Act Density 1.358%

    No Known Activations