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

    Neuronpedia

    INDEX
    Explanations

    elements related to predictive modeling and evaluation of significant factors in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.86
     Monfieur
    -0.72
     图解
    -0.71
    ∎
    -0.71
     Yud
    -0.70
    iastes
    -0.69
     <<<<<<<<<<<<<<
    -0.69
     Aten
    -0.69
     estekak
    -0.69
    ItemBackground
    -0.68
    POSITIVE LOGITS
    就
    1.18
     就
    0.98
    他就
    0.94
    她就
    0.90
    我就
    0.87
    的就
    0.81
    都
    0.80
    便
    0.78
    你就
    0.76
    那就
    0.76
    Act Density 0.034%

    No Known Activations