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

    Neuronpedia

    INDEX
    Explanations

    phrases related to persistence and remaining in a certain state or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.59
    PyExc
    -0.56
    contentLoaded
    -0.52
     nonUne
    -0.50
    таратура
    -0.50
    rigger
    -0.48
    ViewFeatures
    -0.47
     للمعارف
    -0.47
    Jeografia
    -0.44
    Cyfeiriadau
    -0.43
    POSITIVE LOGITS
     remained
    0.79
     remain
    0.79
     stayed
    0.74
     Stay
    0.74
    Stay
    0.72
     stay
    0.72
     retention
    0.71
     stays
    0.70
     Retention
    0.69
    remain
    0.68
    Act Density 0.559%

    No Known Activations