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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating location or origin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.13
    3:0.09
    4:0.11
    5:0.02
    6:0.10
    7:0.25
    8:0.03
    9:0.03
    10:0.05
    11:0.10
    Negative Logits
    ellery
    -1.30
     gif
    -1.26
    gency
    -1.25
    ribute
    -1.21
     CGI
    -1.21
     diarr
    -1.20
    ourcing
    -1.18
     compuls
    -1.18
     volunteer
    -1.17
    andom
    -1.16
    POSITIVE LOGITS
    atown
    1.64
     snipp
    1.40
     Publishers
    1.38
    ritch
    1.38
    Filename
    1.36
    usky
    1.34
     Hague
    1.33
    hesda
    1.33
     pitfalls
    1.31
     footh
    1.23
    Act Density 0.001%

    No Known Activations