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

    Neuronpedia

    INDEX
    Explanations

    details about historical events and characters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to the passage of time and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.05
    3:0.21
    4:0.04
    5:0.07
    6:0.02
    7:0.08
    8:0.05
    9:0.10
    10:0.18
    11:0.09
    Negative Logits
    pick
    -0.91
    ンジ
    -0.90
    del
    -0.88
    cess
    -0.87
    dropping
    -0.87
    uty
    -0.86
    leasing
    -0.84
    Camp
    -0.81
    english
    -0.81
     Scholars
    -0.81
    POSITIVE LOGITS
     hump
    0.88
    ieri
    0.85
    kward
    0.83
    ──
    0.83
     Nunes
    0.82
     comprehension
    0.82
    orius
    0.81
     fundament
    0.80
     happened
    0.80
     applies
    0.79
    Act Density 0.763%

    No Known Activations