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

    Neuronpedia

    INDEX
    Explanations

    verbs related to initiating or starting something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "launched" and its variations, indicating actions related to starting initiatives or campaigns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Son
    -0.67
    ocard
    -0.63
    etry
    -0.62
    GO
    -0.62
     Marketable
    -0.61
    iane
    -0.60
    how
    -0.60
    avering
    -0.60
    Forest
    -0.59
     behold
    -0.58
    POSITIVE LOGITS
    laun
    0.91
    launch
    0.89
    eers
    0.89
    wcs
    0.87
     launching
    0.84
    pad
    0.84
    EStream
    0.82
    hement
    0.80
    eer
    0.76
     laun
    0.76
    Act Density 0.026%

    No Known Activations