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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a combination or integration of elements

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

    combined with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.47
     Wahrheit
    -0.39
    })->
    -0.36
     Chinois
    -0.35
     África
    -0.35
     Grecs
    -0.35
     dàng
    -0.35
    vierno
    -0.35
     Gerechtigkeit
    -0.34
    )—
    -0.34
    POSITIVE LOGITS
    complexContent
    0.66
     utafitiHapana
    0.56
     Normdatei
    0.56
     coupled
    0.54
     AssemblyCulture
    0.54
     combined
    0.52
     autorytatywna
    0.52
     penchant
    0.52
    paralleled
    0.52
    Ӕ
    0.51
    Act Density 0.041%

    No Known Activations