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

    Neuronpedia

    INDEX
    Explanations

    phrases related to debut or making an impact in a particular field

    oai_token-act-pair · gpt-3.5-turbo

    references to significant achievements or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disputes
    -0.66
     WATCHED
    -0.64
    Problem
    -0.63
     Niet
    -0.61
    wr
    -0.60
    planet
    -0.58
    Poll
    -0.58
    rity
    -0.57
     Problem
    -0.57
     looph
    -0.57
    POSITIVE LOGITS
     debut
    1.10
     appearance
    1.03
     splash
    0.96
     appearances
    0.96
     comeback
    0.94
     triumphant
    0.94
     return
    0.85
     cameo
    0.84
     landfall
    0.82
    hift
    0.78
    Act Density 0.084%

    No Known Activations