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

    Neuronpedia

    INDEX
    Explanations

    concepts and phrases related to possibilities and goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erosis
    -0.17
    beh
    -0.15
    rů
    -0.14
    piar
    -0.14
    leases
    -0.14
    utas
    -0.14
    ile
    -0.14
     traj
    -0.14
    leg
    -0.13
    atas
    -0.13
    POSITIVE LOGITS
    ignon
    0.17
    TestingModule
    0.15
     Nich
    0.15
    iskey
    0.15
    Łèĥ½
    0.15
    amoto
    0.14
    ibase
    0.14
    elters
    0.14
     Amen
    0.14
    ZF
    0.14
    Act Density 0.080%

    No Known Activations