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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "imagine" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gewiesen
    -0.70
    BaseActivity
    -0.64
     StatefulWidget
    -0.64
    ⋮
    -0.62
     Cæsar
    -0.61
    ButtonModule
    -0.60
    riwal
    -0.60
    romycin
    -0.58
    DataSetChanged
    -0.58
    Notable
    -0.58
    POSITIVE LOGITS
     imagine
    1.92
     imagining
    1.90
     imagined
    1.79
     imagines
    1.74
    Imagine
    1.74
     Imagine
    1.72
    imagine
    1.68
     IMAG
    1.67
     Imagin
    1.64
     imagin
    1.62
    Act Density 0.100%

    No Known Activations