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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the launch of campaigns or attacks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of initiating or starting campaigns or projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marketable
    -0.75
    Son
    -0.71
    iane
    -0.66
    avering
    -0.64
    GO
    -0.63
    cious
    -0.62
    uth
    -0.61
    etry
    -0.61
    how
    -0.58
    Jose
    -0.58
    POSITIVE LOGITS
    launch
    0.91
    laun
    0.89
    eers
    0.86
    pad
    0.85
     Seym
    0.83
    lishing
    0.81
    wcs
    0.80
     launching
    0.79
    eer
    0.76
    EStream
    0.75
    Act Density 0.034%

    No Known Activations