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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of "highest" or "greatest" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    an
    -0.96
    er
    -0.94
    o
    -0.90
    p
    -0.85
    a
    -0.81
    r
    -0.80
    u
    -0.79
     p
    -0.76
     a
    -0.75
    q
    -0.75
    POSITIVE LOGITS
     greateſt
    1.72
     beſt
    1.68
     healthiest
    1.61
     leaſt
    1.59
     oldest
    1.58
     longest
    1.58
     broadest
    1.58
     myſelf
    1.57
    longest
    1.55
     widest
    1.55
    Act Density 0.094%

    No Known Activations