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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing qualities or statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     active
    -0.15
    aru
    -0.15
    ÙĦاÙģ
    -0.14
    est
    -0.14
    549
    -0.14
     tableau
    -0.13
    .avi
    -0.13
     konkrét
    -0.13
    /table
    -0.13
     Guerr
    -0.13
    POSITIVE LOGITS
    ANDING
    0.15
    InRange
    0.15
    prech
    0.14
    лÑĥÑĩ
    0.14
    igne
    0.14
    PRS
    0.14
    ħn
    0.13
     Dann
    0.13
    plib
    0.13
    imagin
    0.13
    Act Density 0.208%

    No Known Activations