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

    Neuronpedia

    INDEX
    Explanations

    phrases related to organized plans or systems

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various schemes, particularly those related to political or economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parenthood
    -0.71
     Ink
    -0.70
    Bott
    -0.66
    bum
    -0.66
    pez
    -0.64
    racted
    -0.64
    imil
    -0.62
    hib
    -0.61
    Ear
    -0.61
    omatic
    -0.61
    POSITIVE LOGITS
     scheme
    3.94
     schemes
    3.08
     Scheme
    2.70
    sche
    1.54
     plan
    1.32
     sche
    1.29
     arrangement
    1.25
     scam
    1.23
    Sche
    1.18
     programme
    1.17
    Act Density 0.020%

    No Known Activations