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

    Neuronpedia

    INDEX
    Explanations

    assertive language related to personal experiences and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meille
    -0.79
     nakalista
    -0.76
     honom
    -0.75
     avoient
    -0.66
    THEY
    -0.66
     auroit
    -0.66
     Wikimedijinoj
    -0.65
    它
    -0.64
    OfThe
    -0.63
     varandra
    -0.63
    POSITIVE LOGITS
     be
    0.51
     Geraadpleegd
    0.49
     herre
    0.49
     ensure
    0.49
    "?>
    0.47
     want
    0.46
    ‌
    0.45
    UCE
    0.45
     i
    0.45
     both
    0.44
    Act Density 0.332%

    No Known Activations