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

    Neuronpedia

    INDEX
    Explanations

    phrases and terminology related to evidence and research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.62
    -0.57
    expandindo
    -0.50
     EconPapers
    -0.47
     ModelExpression
    -0.46
    #+#
    -0.45
    LOYEES
    -0.44
    findpost
    -0.44
    RenderAtEndOf
    -0.44
     Lightboxes
    -0.43
    POSITIVE LOGITS
     evidence
    0.92
    evidence
    0.80
    证据
    0.72
     evidencia
    0.68
     preuve
    0.67
     evidences
    0.65
    Evidence
    0.64
     EVIDENCE
    0.64
     факты
    0.63
     membuk
    0.62
    Act Density 0.952%

    No Known Activations