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

    Neuronpedia

    INDEX
    Explanations

    terms related to stability and change over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .DropTable
    -0.17
     aggress
    -0.16
    aat
    -0.15
     Goose
    -0.15
    ếu
    -0.14
     assembly
    -0.14
    Radians
    -0.14
    away
    -0.14
    ç¨
    -0.14
    one
    -0.13
    POSITIVE LOGITS
    867
    0.17
     halt
    0.17
    ABEL
    0.15
    plib
    0.15
     pond
    0.15
     McKenzie
    0.14
    íļĮ
    0.14
     Reeves
    0.14
     dok
    0.14
    rophe
    0.13
    Act Density 0.286%

    No Known Activations