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

    Neuronpedia

    INDEX
    Explanations

    locations specifically associated with geological features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.04
    2:0.06
    3:0.04
    4:0.05
    5:0.04
    6:0.23
    7:0.06
    8:0.05
    9:0.19
    10:0.04
    11:0.04
    Negative Logits
     Huck
    -5.20
     FML
    -3.78
    Haunted
    -3.75
     CAS
    -3.71
     Jac
    -3.38
    �醒
    -3.36
     carn
    -3.32
     Pompe
    -3.29
     cess
    -3.26
     Maced
    -3.23
    POSITIVE LOGITS
     Sharp
    9.04
    Sharp
    7.82
    sharp
    6.29
     sharp
    4.75
     shar
    4.68
     Durant
    4.25
     sharper
    4.15
     Shot
    4.00
    knife
    3.99
     knives
    3.88
    Act Density 0.001%

    No Known Activations