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

    Neuronpedia

    INDEX
    Explanations

    references to third parties or third-party interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     consig
    -0.56
    warzys
    -0.49
    λεί
    -0.48
    iramente
    -0.48
     consign
    -0.47
     aspi
    -0.47
    baijan
    -0.46
    odyne
    -0.46
    belline
    -0.45
    ikan
    -0.45
    POSITIVE LOGITS
     Third
    2.08
    Third
    2.05
     third
    1.97
    third
    1.96
     THIRD
    1.84
     terceiro
    1.73
    THIRD
    1.71
     thirds
    1.69
    III
    1.67
    thirds
    1.66
    Act Density 0.083%

    No Known Activations