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

    Neuronpedia

    INDEX
    Explanations

    words related to change and improvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARGER
    -0.16
     slightly
    -0.15
    лим
    -0.15
    zk
    -0.15
    ấn
    -0.15
    imore
    -0.14
     unequal
    -0.14
    %č↵
    -0.13
     Larger
    -0.13
     Goldberg
    -0.13
    POSITIVE LOGITS
     significant
    0.61
    significant
    0.52
     dramatic
    0.52
     Significant
    0.49
     substantial
    0.45
     Dram
    0.45
     signific
    0.45
     drastic
    0.44
     знаÑĩ
    0.40
     considerable
    0.40
    Act Density 0.540%

    No Known Activations