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

    Neuronpedia

    INDEX
    Explanations

    phrases related to common misconceptions or overlooked concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __':
    -0.76
     Majefty
    -0.72
    ̍t
    -0.71
     дописавши
    -0.69
     purpoſe
    -0.66
    DockStyle
    -0.66
    Tikang
    -0.65
    ſelves
    -0.65
     OFDb
    -0.64
    __":
    -0.64
    POSITIVE LOGITS
    BeginContext
    0.68
     people
    0.52
    ยม
    0.50
     принято
    0.49
     often
    0.48
     gente
    0.47
     misconception
    0.47
     AttributeSet
    0.47
     go
    0.47
     считается
    0.46
    Act Density 0.339%

    No Known Activations