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

    Neuronpedia

    INDEX
    Explanations

    phrases related to typing and text input actions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    featureID
    -0.73
     BoxDecoration
    -0.59
     zewnętrzne
    -0.57
     lenker
    -0.57
    colorbar
    -0.55
    oneofs
    -0.54
    EReference
    -0.54
    IZI
    -0.54
    apimachinery
    -0.53
    newtheorem
    -0.51
    POSITIVE LOGITS
    nEnter
    0.84
    Typing
    0.76
     Typing
    0.73
     typed
    0.72
     typing
    0.67
    typed
    0.66
     keypad
    0.62
     keys
    0.60
    TypedValue
    0.60
    Twas
    0.60
    Act Density 0.028%

    No Known Activations