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

    Neuronpedia

    INDEX
    Explanations

    expressions of concern or worry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Besides" or similar transitional words

    np_acts-logits-general · gemini-2.0-flash

    besides plus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ObjectContext
    -0.71
    InjectAttribute
    -0.68
    horabuena
    -0.62
    CloseOperation
    -0.58
     betweenstory
    -0.57
     snippetHide
    -0.56
    arResult
    -0.55
    ViewImports
    -0.54
     AssemblyCompany
    -0.53
     Waray
    -0.52
    POSITIVE LOGITS
     Plus
    1.94
     besides
    1.92
     plus
    1.90
    Plus
    1.89
    Besides
    1.83
     Besides
    1.80
    besides
    1.74
    plus
    1.74
     PLUS
    1.60
    况
    1.40
    Act Density 0.442%

    No Known Activations