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

    Neuronpedia

    INDEX
    Explanations

    locations and physical descriptions in a variety of contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    specific locations and geographical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.01
    2:0.06
    3:0.10
    4:0.02
    5:0.09
    6:0.03
    7:0.09
    8:0.17
    9:0.05
    10:0.16
    11:0.09
    Negative Logits
     brakes
    -1.08
    omever
    -0.95
    UTC
    -0.95
    Reloaded
    -0.94
     sqor
    -0.86
     inhibitors
    -0.84
    ÍÍ
    -0.83
     skeptics
    -0.82
    theless
    -0.82
    urtles
    -0.82
    POSITIVE LOGITS
    opolis
    1.11
    opian
    1.05
    orld
    1.04
     district
    1.02
    torn
    1.02
    iverse
    0.97
     region
    0.94
    taboola
    0.93
     orbit
    0.93
     arena
    0.92
    Act Density 1.033%

    No Known Activations