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

    Neuronpedia

    INDEX
    Explanations

    references to "back" in various contexts, particularly actions and forms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.92
    °•
    -0.87
     Larsen
    -0.86
    Gemeinden
    -0.85
    mongoose
    -0.82
    tershire
    -0.82
    ✨:
    -0.82
    ']>;
    -0.81
    CSA
    -0.81
    leyball
    -0.80
    POSITIVE LOGITS
    Back
    1.30
     Back
    1.30
    BACK
    1.24
    back
    1.20
     BACK
    1.13
     backs
    1.10
     Backman
    1.05
     back
    1.00
    backs
    0.96
    btnBack
    0.94
    Act Density 0.155%

    No Known Activations