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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating introduction or transition between topics

    oai_token-act-pair · gpt-3.5-turbo

    the word "brings" at high frequencies, indicating a focus on actions or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FactoryReloaded
    -0.73
    raid
    -0.72
    hemat
    -0.69
    livious
    -0.67
    inyl
    -0.67
    dating
    -0.65
    schild
    -0.63
    uchs
    -0.63
    roman
    -0.61
     ellipt
    -0.59
    POSITIVE LOGITS
    glers
    0.78
    ĸļ
    0.78
     Cth
    0.75
     Came
    0.70
    ources
    0.68
    backs
    0.67
    awed
    0.66
    entious
    0.66
     forward
    0.66
     ashore
    0.65
    Act Density 0.016%

    No Known Activations