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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or notable names

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article 'a' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    efficient
    -0.76
     ethic
    -0.74
    effic
    -0.73
    acid
    -0.72
    inson
    -0.70
    cells
    -0.69
    ignore
    -0.68
    intelligence
    -0.68
    peak
    -0.67
    ··
    -0.67
    POSITIVE LOGITS
     slew
    1.22
     plethora
    1.17
     revamped
    1.08
     whopping
    1.07
     redesigned
    1.05
     variety
    0.99
     multitude
    0.98
     brand
    0.96
     new
    0.95
     bunch
    0.95
    Act Density 0.314%

    No Known Activations