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

    Neuronpedia

    INDEX
    Explanations

    plans or strategies mentioned in sentences

    oai_token-act-pair · gpt-3.5-turbo

    mentions of plans or strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dab
    -0.63
    NetMessage
    -0.62
     Thumbnails
    -0.60
    ï¸ı
    -0.59
     Trophy
    -0.59
    nces
    -0.58
     disbelief
    -0.58
     experien
    -0.57
    Naz
    -0.56
     Robots
    -0.55
    POSITIVE LOGITS
    emaker
    1.06
    isphere
    1.05
    ks
    1.01
    etary
    0.97
    ters
    0.96
    ets
    0.89
    ologies
    0.88
    meal
    0.86
    ter
    0.85
     outline
    0.82
    Act Density 0.051%

    No Known Activations