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

    Neuronpedia

    INDEX
    Explanations

    punctuation and certain grammatical structures in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.02
    2:0.05
    3:0.04
    4:0.03
    5:0.03
    6:0.22
    7:0.04
    8:0.06
    9:0.27
    10:0.04
    11:0.04
    Negative Logits
     Carm
    -4.23
     Mellon
    -3.85
    gem
    -3.80
     Lloyd
    -3.66
     Oliv
    -3.56
     peach
    -3.46
     Elliott
    -3.37
    icker
    -3.24
    angel
    -3.22
    kl
    -3.21
    POSITIVE LOGITS
     Sur
    8.57
    Sur
    6.36
    sur
    6.21
     SUR
    5.92
     sur
    5.51
     SAR
    5.36
     Surf
    4.91
     surfing
    4.84
     surf
    4.49
     Lur
    4.02
    Act Density 0.001%

    No Known Activations