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

    Neuronpedia

    INDEX
    Explanations

    terms related to comparisons and distinctions among groups

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     celle
    -0.52
     quello
    -0.49
    ArrowToggle
    -0.44
     celui
    -0.43
     lượt
    -0.43
    oa̍t
    -0.42
    Recap
    -0.41
    Personensuche
    -0.41
    Already
    -0.40
     pourtant
    -0.39
    POSITIVE LOGITS
    RenderAtEndOf
    0.82
    TestingModule
    0.63
    vidla
    0.63
    carus
    0.63
    utilisons
    0.61
     depositphotos
    0.61
     fubject
    0.59
     surla
    0.59
     Hacker
    0.58
     Theorem
    0.58
    Act Density 0.051%

    No Known Activations