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

    Neuronpedia

    INDEX
    Explanations

    references to aspirations or desires

    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
    -0.82
    arius
    -0.72
    oute
    -0.71
    idges
    -0.68
    ãĥĺãĥ©
    -0.67
    ahn
    -0.65
    andise
    -0.63
    anti
    -0.62
    ahon
    -0.62
    Fed
    -0.61
    POSITIVE LOGITS
     dreaming
    0.92
    tek
    0.92
    scape
    0.90
     dreams
    0.89
     dream
    0.88
    dream
    0.86
    liner
    0.79
    hack
    0.78
    spe
    0.77
     dreamed
    0.76
    Act Density 0.026%

    No Known Activations