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

    Neuronpedia

    INDEX
    Explanations

    references to downgrading, depreciation, or reduction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "down" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andum
    -0.68
    9999
    -0.66
    ãĥŁ
    -0.56
    ë
    -0.56
     avail
    -0.56
    Discover
    -0.55
    ¶ħ
    -0.55
    tein
    -0.55
    000000
    -0.54
     Pros
    -0.54
    POSITIVE LOGITS
    graded
    1.43
    grading
    1.30
    LOAD
    1.29
    stairs
    1.28
    pour
    1.14
    grades
    1.14
    hill
    1.06
    loaded
    1.03
    grade
    0.97
    sized
    0.96
    Act Density 0.045%

    No Known Activations