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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to interpersonal relationships and societal complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    995
    -0.15
    asser
    -0.15
    IVEN
    -0.14
    ureau
    -0.14
    chluss
    -0.14
     Wand
    -0.14
     ARC
    -0.14
    izon
    -0.13
    isson
    -0.13
    .PO
    -0.13
    POSITIVE LOGITS
    endas
    0.16
    ht
    0.14
    itus
    0.14
    alu
    0.14
    á»ĩ
    0.14
    rom
    0.14
    ottes
    0.14
    .SimpleButton
    0.14
     fi
    0.14
    otte
    0.14
    Act Density 0.508%

    No Known Activations