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

    Neuronpedia

    INDEX
    Explanations

    numerical data, specifically related to values and counts in a table format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ound
    -0.15
    undle
    -0.15
     l
    -0.14
     meg
    -0.14
     narrow
    -0.14
     if
    -0.14
    oken
    -0.14
     Tribe
    -0.13
    uper
    -0.13
    757
    -0.13
    POSITIVE LOGITS
    лÑĥги
    0.19
     applicationWill
    0.15
     [âĢ¦]...↵
    0.15
    mbH
    0.14
    MUX
    0.14
    unky
    0.14
    anim
    0.14
    ÐĴÐIJ
    0.13
     درÛĮ
    0.13
    erdale
    0.13
    Act Density 0.011%

    No Known Activations