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

    Neuronpedia

    INDEX
    Explanations

    references to building floors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.11
    3:0.05
    4:0.07
    5:0.04
    6:0.11
    7:0.04
    8:0.05
    9:0.06
    10:0.22
    11:0.15
    Negative Logits
    Hur
    -1.63
    Crit
    -1.57
    ophen
    -1.54
     comed
    -1.49
     skept
    -1.46
     Kurd
    -1.43
     criticisms
    -1.41
    gio
    -1.40
     pudding
    -1.38
     criticism
    -1.37
    POSITIVE LOGITS
     286
    1.62
     386
    1.52
     DOC
    1.43
     NEC
    1.41
     seniors
    1.38
    amba
    1.35
     undergoing
    1.34
     CPC
    1.33
     Metro
    1.32
    ..........
    1.32
    Act Density 0.001%

    No Known Activations