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

    Neuronpedia

    INDEX
    Explanations

    phrases related to experimental and analytical processes in scientific contexts

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

    Prepositions following activating tokens

    np_acts-logits-general · gemini-2.0-flash

    applied or used on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AspNetCore
    -0.52
    routeProvider
    -0.52
    HostException
    -0.47
    featureID
    -0.47
    UnsafeEnabled
    -0.46
    AccessorTable
    -0.46
    PreferredItem
    -0.44
    MemoryWarning
    -0.44
     EconPapers
    -0.43
    ########.
    -0.43
    POSITIVE LOGITS
     applied
    0.89
     asupra
    0.82
    applied
    0.77
     terhadap
    0.75
     върху
    0.75
    对
    0.70
     onto
    0.65
    對
    0.65
    Applied
    0.63
     aplicado
    0.62
    Act Density 1.584%

    No Known Activations