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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "best" and its variations, indicating a focus on quality or superiority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "Best" or "best"

    np_acts-logits-general · gemini-2.0-flash

    best followed by superlatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    -0.76
    an
    -0.70
    a
    -0.62
    io
    -0.60
    q
    -0.59
    k
    -0.59
    o
    -0.59
    r
    -0.56
    h
    -0.56
    ER
    -0.56
    POSITIVE LOGITS
     healthiest
    1.04
     lightest
    1.00
     darkest
    0.99
     possible
    0.99
    ariest
    0.98
     happiest
    0.97
     beſt
    0.97
    BEST
    0.95
     safest
    0.95
    possible
    0.95
    Act Density 0.127%

    No Known Activations