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

    Neuronpedia

    INDEX
    Explanations

    elements of interpersonal relationships and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agnitude
    -0.15
    ->__
    -0.15
    OfClass
    -0.15
    ottes
    -0.15
    plash
    -0.14
    éģĩ
    -0.14
    assi
    -0.14
    èm
    -0.14
    太éĺ³åŁİ
    -0.14
    hints
    -0.14
    POSITIVE LOGITS
     latter
    0.17
    hea
    0.16
    дÑı
    0.16
     обо
    0.16
     offering
    0.15
     later
    0.15
    opo
    0.15
    both
    0.15
    omo
    0.14
     upon
    0.14
    Act Density 0.521%

    No Known Activations