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

    Neuronpedia

    INDEX
    Explanations

    the presence of references and citations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.07
    3:0.09
    4:0.08
    5:0.07
    6:0.07
    7:0.08
    8:0.08
    9:0.10
    10:0.08
    11:0.08
    Negative Logits
     rewards
    -2.62
     addon
    -2.62
    azel
    -2.55
    amaru
    -2.50
    pleting
    -2.47
     scrolls
    -2.43
    ctica
    -2.40
     ware
    -2.40
     deadlines
    -2.38
    ticket
    -2.36
    POSITIVE LOGITS
    nesota
    2.78
    CLA
    2.66
     1968
    2.58
     Fres
    2.57
     1916
    2.54
     Lisp
    2.52
     1913
    2.51
     Orleans
    2.50
     Hornets
    2.47
     Ferguson
    2.41
    Act Density 0.000%

    No Known Activations