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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to using something as a particular purpose or for a specific function

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the function or purpose of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Os
    -0.79
    akings
    -0.76
    errors
    -0.75
    yright
    -0.72
    roying
    -0.70
    ModLoader
    -0.69
    akis
    -0.68
    ukemia
    -0.68
    LINE
    -0.67
     Rebell
    -0.66
    POSITIVE LOGITS
     leverage
    1.02
     template
    0.92
     filler
    0.90
     shorthand
    0.88
     guideline
    0.88
     fodder
    0.85
     surrogate
    0.82
     inspiration
    0.82
     benchmark
    0.82
     pretext
    0.81
    Act Density 0.114%

    No Known Activations