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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to engineering and construction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to processes, structures, and organizational concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovie
    -0.55
    ifier
    -0.51
    rower
    -0.49
    utra
    -0.49
    Downloadha
    -0.48
     WATCHED
    -0.48
    agame
    -0.48
    etsk
    -0.47
    pherd
    -0.47
    uden
    -0.46
    POSITIVE LOGITS
     emergencies
    0.53
     intermedi
    0.53
     proportions
    0.52
     purposes
    0.51
    bugs
    0.50
     donors
    0.50
     rivals
    0.48
     shores
    0.48
     margins
    0.48
     levels
    0.48
    Act Density 1.486%

    No Known Activations