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
    494
    -0.15
    ulle
    -0.14
    rez
    -0.14
    anders
    -0.14
    rais
    -0.14
     ÐĴид
    -0.14
    нимаÑĤÑĮ
    -0.14
    itler
    -0.14
    igen
    -0.14
     slight
    -0.14
    POSITIVE LOGITS
    -scale
    0.26
    /small
    0.16
    gest
    0.16
    主任
    0.16
    Scale
    0.15
    scale
    0.15
    armor
    0.15
     scale
    0.14
    gger
    0.14
    grunt
    0.14
    Act Density 0.035%

    No Known Activations