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

    Neuronpedia

    INDEX
    Explanations

    phrases related to publication and data integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [array
    -0.14
     Leone
    -0.14
    507
    -0.14
     rej
    -0.14
    803
    -0.14
    hay
    -0.14
    ucci
    -0.14
    orth
    -0.13
     Sens
    -0.13
     Depression
    -0.13
    POSITIVE LOGITS
    елик
    0.17
    ɵ
    0.16
    allel
    0.15
    iyim
    0.15
    eced
    0.15
    ivals
    0.14
    Ymd
    0.14
    λικ
    0.14
    _grad
    0.14
    elize
    0.14
    Act Density 0.092%

    No Known Activations