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

    Neuronpedia

    INDEX
    Explanations

    key technical terms and concepts related to research methodologies and frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.87
     виправивши
    -0.78
    SourceChecksum
    -0.73
     pronti
    -0.65
    følgelig
    -0.61
     AssemblyCompany
    -0.61
     bezeichneter
    -0.61
    LookAnd
    -0.60
     facie
    -0.60
     Ignorance
    -0.59
    POSITIVE LOGITS
     rather
    0.90
     instead
    0.83
     unlike
    0.77
    unlike
    0.72
    rather
    0.72
     Rather
    0.71
    而非
    0.71
    instead
    0.70
    而不是
    0.69
    Rather
    0.68
    Act Density 0.775%

    No Known Activations