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

    Neuronpedia

    INDEX
    Explanations

    references to features in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+
    -0.50
    RefNanny
    -0.50
    understanding
    -0.50
     evacu
    -0.47
     Wounded
    -0.46
    Injury
    -0.43
    centralwidget
    -0.43
     onCancelled
    -0.43
     allAfrica
    -0.42
     Injury
    -0.41
    POSITIVE LOGITS
     feature
    1.07
     features
    1.04
     feat
    0.78
     featuring
    0.77
     featured
    0.75
     Featuring
    0.73
    Featuring
    0.73
    featuring
    0.70
    features
    0.68
     FEATURES
    0.67
    Act Density 0.427%

    No Known Activations