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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate ease, smoothness, or enjoyment in processes or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.59
    MemoryWarning
    -0.56
    Diweddarwch
    -0.52
    ValueGenerated
    -0.51
    mtable
    -0.49
     persil
    -0.49
    SizeF
    -0.48
     iprot
    -0.47
    CaseSensitive
    -0.46
    kenstock
    -0.45
    POSITIVE LOGITS
     enjoyable
    0.84
    WriteTagHelper
    0.72
    LookAnd
    0.70
    ftagPool
    0.70
     easier
    0.68
     experience
    0.66
     Easier
    0.65
     Theſe
    0.65
     slog
    0.64
     fun
    0.64
    Act Density 0.172%

    No Known Activations