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

    Neuronpedia

    INDEX
    Explanations

    individual names, particularly notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.08
    3:0.08
    4:0.09
    5:0.07
    6:0.08
    7:0.08
    8:0.08
    9:0.07
    10:0.07
    11:0.08
    Negative Logits
    IGHTS
    -2.68
     fumes
    -2.58
    */(
    -2.52
    isconsin
    -2.52
     strugg
    -2.41
     sparks
    -2.38
     encount
    -2.36
     firefighter
    -2.30
     warn
    -2.27
     CW
    -2.27
    POSITIVE LOGITS
    rax
    2.80
     Epstein
    2.54
     Pain
    2.50
     DirectX
    2.50
     Zin
    2.42
     Levine
    2.41
    614
    2.39
     Payne
    2.38
    shirts
    2.36
    Roberts
    2.34
    Act Density 0.000%

    No Known Activations