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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the letter "s" in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.37
    2:0.05
    3:0.04
    4:0.04
    5:0.15
    6:0.03
    7:0.02
    8:0.06
    9:0.04
    10:0.04
    11:0.02
    Negative Logits
    whelming
    -1.95
    stood
    -1.92
    amer
    -1.80
     Bret
    -1.77
    ��
    -1.75
    sold
    -1.72
    united
    -1.71
     AMER
    -1.64
    Victoria
    -1.61
     Californ
    -1.57
    POSITIVE LOGITS
    ip
    3.11
    IP
    2.52
    ips
    2.23
    isco
    2.20
    ipt
    2.14
     Rip
    2.08
    iped
    2.05
     IP
    2.00
    iffe
    1.94
    ipop
    1.94
    Act Density 0.002%

    No Known Activations