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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leaving and escape

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sudoku
    -0.45
    квар
    -0.40
     guess
    -0.39
    <eos>
    -0.39
     suppose
    -0.38
    
    -0.38
    +:+
    -0.38
     Trent
    -0.37
     result
    -0.37
    ടി
    -0.37
    POSITIVE LOGITS
     Leaving
    1.05
     leaving
    0.97
    Leaving
    0.95
     meninggalkan
    0.93
     quitté
    0.93
    IntoConstraints
    0.92
    AndEndTag
    0.92
    離開
    0.89
     beginnetje
    0.89
     quitted
    0.89
    Act Density 0.275%

    No Known Activations