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

    Neuronpedia

    INDEX
    Explanations

    references to household and equivalence concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     uovo
    -0.76
     expéri
    -0.76
     дол
    -0.74
     sèche
    -0.73
    ọa
    -0.72
    chaik
    -0.71
     Hera
    -0.71
     Hew
    -0.71
     attre
    -0.70
     Excelsior
    -0.69
    POSITIVE LOGITS
    )")
    0.86
    erweise
    0.86
    ]")
    0.80
     recast
    0.79
    IANCE
    0.77
    equity
    0.77
    смотрен
    0.77
     Să
    0.77
    ))^
    0.76
    ?")
    0.76
    Act Density 0.104%

    No Known Activations