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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms related to governmental and bureaucratic contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.02
    2:0.15
    3:0.07
    4:0.18
    5:0.05
    6:0.03
    7:0.07
    8:0.08
    9:0.04
    10:0.13
    11:0.07
    Negative Logits
    cca
    -1.09
     Liter
    -1.09
    glers
    -1.07
    lance
    -1.07
    adh
    -1.05
    appropriate
    -1.02
     Enh
    -0.99
     tamp
    -0.98
     Reincarn
    -0.97
    thood
    -0.97
    POSITIVE LOGITS
     Bohem
    1.19
     distances
    1.16
     rest
    1.12
    ulkan
    1.12
     generations
    1.08
    ortment
    1.06
    Aust
    1.02
    arching
    1.02
    き
    1.01
    ipment
    1.00
    Act Density 0.018%

    No Known Activations