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

    Neuronpedia

    INDEX
    Explanations

    phrases that highlight causal relationships or reasons for events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.62
     capables
    -0.62
    :✨
    -0.58
    TintMode
    -0.58
    propTypes
    -0.56
    Demografie
    -0.56
    moveToFirst
    -0.55
    GraphicsUnit
    -0.55
    andExpect
    -0.54
    isSuccessful
    -0.54
    POSITIVE LOGITS
     lack
    1.70
     insufficient
    1.33
    lack
    1.32
    Lack
    1.30
     Lack
    1.21
     inability
    1.19
     inadequate
    1.13
     poor
    1.12
     manque
    1.08
     Insufficient
    1.04
    Act Density 0.832%

    No Known Activations