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

    Neuronpedia

    INDEX
    Explanations

    verbs related to descent or lowering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inness
    -0.17
    bian
    -0.16
    ж
    -0.15
    ÑĢел
    -0.15
    igon
    -0.15
    itag
    -0.15
    aurant
    -0.15
    esters
    -0.14
    cles
    -0.14
     up
    -0.14
    POSITIVE LOGITS
    graded
    0.24
    grades
    0.21
    wards
    0.20
    -down
    0.20
    /up
    0.19
    ey
    0.19
    sville
    0.19
    grading
    0.19
    played
    0.18
    ward
    0.18
    Act Density 0.057%

    No Known Activations