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

    Neuronpedia

    INDEX
    Explanations

    the word "imagine."

    oai_token-act-pair · gpt-3.5-turbo

    phrases prompting hypothetical scenarios or thought experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bard
    -0.87
    ged
    -0.75
    inals
    -0.75
    die
    -0.73
    fund
    -0.68
    hide
    -0.66
    woods
    -0.66
    unker
    -0.65
    inance
    -0.63
    wa
    -0.63
    POSITIVE LOGITS
    ĸļ
    0.92
    lihood
    0.83
     how
    0.74
    ufact
    0.73
     imagine
    0.72
     msec
    0.70
     aloud
    0.69
    eers
    0.68
    orial
    0.67
     imagining
    0.65
    Act Density 0.027%

    No Known Activations