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

    Neuronpedia

    INDEX
    Explanations

    concepts related to societal dynamics and interpersonal relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Савезне
    -0.81
     مرئيه
    -0.76
    }>;
    -0.72
    "])
    -0.71
    ]--;
    -0.70
    )";
    -0.69
     déput
    -0.67
    }')
    -0.65
    /$',
    -0.64
     '{@
    -0.64
    POSITIVE LOGITS
     sehari
    0.69
    ParallelGroup
    0.64
     sendiri
    0.61
    曖昧さ回避
    0.54
    felf
    0.51
     alone
    0.51
    messer
    0.48
    Referências
    0.48
    конец
    0.47
     origini
    0.47
    Act Density 0.633%

    No Known Activations