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

    Neuronpedia

    INDEX
    Explanations

    topics related to trust and relationships in various contexts, including education and personal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anes
    -0.17
    bstract
    -0.16
    CLU
    -0.15
    нг
    -0.15
    rio
    -0.15
    arges
    -0.14
    jem
    -0.14
    zc
    -0.14
    179
    -0.14
     ï½ľ
    -0.14
    POSITIVE LOGITS
     foreign
    0.17
     Pine
    0.17
    foreign
    0.16
     ÑĩÑĥж
    0.16
     alien
    0.15
     trans
    0.15
    ÑģÑĤÑĢов
    0.14
    rung
    0.14
    imir
    0.14
     reap
    0.14
    Act Density 0.276%

    No Known Activations