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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating location and time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.15
    3:0.07
    4:0.13
    5:0.03
    6:0.04
    7:0.16
    8:0.04
    9:0.05
    10:0.14
    11:0.11
    Negative Logits
     illum
    -1.43
    itialized
    -1.24
    uncle
    -1.20
    cffffcc
    -1.20
     prayers
    -1.18
     congratulate
    -1.13
    landish
    -1.13
     insepar
    -1.12
     congratulated
    -1.12
    ointed
    -1.11
    POSITIVE LOGITS
     Disclosure
    1.28
     Tulsa
    1.22
     Chattanooga
    1.22
     HELL
    1.19
     Britain
    1.16
     nationwide
    1.13
     Wilmington
    1.10
     NI
    1.08
     Nine
    1.07
     Rochester
    1.07
    Act Density 0.208%

    No Known Activations