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

    Neuronpedia

    INDEX
    Explanations

    definite articles paired with superlative adjectives or notable descriptions

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

    "One of the"

    np_acts-logits-general · gemini-2.0-flash

    one of the most

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Entire
    -0.56
    Semitism
    -0.54
    Second
    -0.52
     Secondly
    -0.52
    ượ
    -0.51
     opportunity
    -0.49
    Secondly
    -0.47
     odpowied
    -0.47
    isNaN
    -0.47
     addition
    -0.47
    POSITIVE LOGITS
     few
    1.27
     many
    1.10
    few
    0.98
     FEW
    0.92
    Few
    0.91
     MANY
    0.91
    many
    0.89
     reasons
    0.86
     earliest
    0.86
     wenigen
    0.84
    Act Density 0.159%

    No Known Activations