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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progress, change, or development over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    change over time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noDo
    -0.69
     ſte
    -0.61
     ſche
    -0.60
    styleType
    -0.59
    ViewImports
    -0.59
    OGND
    -0.59
    principalColumn
    -0.57
    expandindo
    -0.56
    windowFixed
    -0.56
     poro
    -0.54
    POSITIVE LOGITS
     sejak
    0.48
     since
    0.48
     sinds
    0.47
     depuis
    0.46
     mudou
    0.44
    相比
    0.44
     zmieni
    0.43
     desde
    0.43
     evolved
    0.42
     cambiado
    0.41
    Act Density 0.020%

    No Known Activations