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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "large" and its variations, indicating a focus on size or scale

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouro
    -0.16
     slightest
    -0.16
    yonel
    -0.15
    bis
    -0.15
    ral
    -0.14
    rary
    -0.14
    chter
    -0.14
     slight
    -0.14
    sembl
    -0.13
    нимаÑĤÑĮ
    -0.13
    POSITIVE LOGITS
    -scale
    0.31
    (er
    0.20
     Livingston
    0.16
    sword
    0.15
    /big
    0.15
    /small
    0.15
    acre
    0.15
     Enough
    0.15
     enough
    0.15
    arg
    0.15
    Act Density 0.048%

    No Known Activations