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

    Neuronpedia

    INDEX
    Explanations

    terms related to decomposition and complex systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igen
    -0.17
    ured
    -0.15
    avage
    -0.15
    innen
    -0.14
    asier
    -0.14
    enÃŃ
    -0.14
    pawn
    -0.14
    umper
    -0.14
    alement
    -0.14
    vant
    -0.14
    POSITIVE LOGITS
    mission
    0.19
    pletely
    0.18
    ission
    0.18
    posite
    0.17
    preh
    0.17
    reh
    0.17
    modity
    0.17
    prehensive
    0.17
    rade
    0.17
    arrison
    0.17
    Act Density 0.031%

    No Known Activations