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

    Neuronpedia

    INDEX
    Explanations

    arguments or propositions related to plans and suggestions

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

    imagining hypothetical situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    السكان
    -0.43
     zwykle
    -0.43
     Trotzdem
    -0.42
    Dziękuję
    -0.40
    相変わらず
    -0.39
     çoğu
    -0.39
     glück
    -0.38
     sobrevivir
    -0.38
     verhält
    -0.38
     thankfully
    -0.38
    POSITIVE LOGITS
     imagine
    0.89
     Imagine
    0.87
    imagine
    0.82
    Imagine
    0.79
     Wouldn
    0.75
    Wouldn
    0.75
     imagin
    0.72
     idea
    0.70
     would
    0.68
     imagining
    0.68
    Act Density 0.048%

    No Known Activations