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

    Neuronpedia

    INDEX
    Explanations

    terms related to aspirations or hopes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of dreams or aspirations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avis
    -0.86
    idges
    -0.74
    arius
    -0.73
    ãĥĺãĥ©
    -0.70
    anti
    -0.66
    oute
    -0.64
    ribut
    -0.64
    iquette
    -0.62
    idated
    -0.62
    Effective
    -0.62
    POSITIVE LOGITS
    tek
    0.88
    scape
    0.86
     dreaming
    0.84
     dreams
    0.81
     dream
    0.80
    smanship
    0.80
    hack
    0.79
     fulfilled
    0.78
    spe
    0.78
     dreamed
    0.75
    Act Density 0.027%

    No Known Activations