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

    Neuronpedia

    INDEX
    Explanations

    phrases that prompt visualization or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    providedIn
    -0.73
     StatefulWidget
    -0.69
    gewiesen
    -0.63
    strix
    -0.61
    τως
    -0.61
    ⋮
    -0.59
    ButtonModule
    -0.58
     tông
    -0.56
    geführt
    -0.56
     poule
    -0.55
    POSITIVE LOGITS
     imagine
    1.68
     imagining
    1.67
     Imagine
    1.56
     IMAG
    1.55
     imagines
    1.54
    Imagine
    1.53
     imagined
    1.51
    imagine
    1.50
     imagin
    1.48
     Imagin
    1.43
    Act Density 0.108%

    No Known Activations