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

    Neuronpedia

    INDEX
    Explanations

    words indicating locations or spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.08
    4:0.08
    5:0.08
    6:0.09
    7:0.08
    8:0.08
    9:0.08
    10:0.06
    11:0.09
    Negative Logits
    ğ
    -1.75
    ��
    -1.61
     Gaul
    -1.60
     Samson
    -1.56
     Argon
    -1.55
    >>>>>>>>
    -1.52
    】
    -1.49
     Catalonia
    -1.49
     Rodriguez
    -1.47
    riks
    -1.47
    POSITIVE LOGITS
    imum
    2.01
    conn
    1.78
    estate
    1.74
    itutional
    1.70
    ignt
    1.66
    incible
    1.64
     dorm
    1.62
    abit
    1.59
    istant
    1.55
    idate
    1.53
    Act Density 0.000%

    No Known Activations