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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exclusivity or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.11
    2:0.07
    3:0.08
    4:0.07
    5:0.07
    6:0.08
    7:0.08
    8:0.09
    9:0.07
    10:0.07
    11:0.08
    Negative Logits
     Azerbaijan
    -2.93
    istor
    -2.87
    nikov
    -2.84
    onian
    -2.83
     Soviets
    -2.81
     USSR
    -2.77
     PCB
    -2.76
    Soviet
    -2.73
     Protoss
    -2.73
     libel
    -2.72
    POSITIVE LOGITS
     Fallen
    2.66
     
    2.60
     ED
    2.60
    HS
    2.59
     Eag
    2.54
    BRE
    2.46
     Hallow
    2.45
    nces
    2.42
     priorities
    2.41
     Trick
    2.30
    Act Density 0.000%

    No Known Activations