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

    Neuronpedia

    INDEX
    Explanations

    references to financial transactions or monetary amounts

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     warp
    -0.68
    rick
    -0.67
    XPATH
    -0.66
    thâu
    -0.60
     tasche
    -0.59
     Warp
    -0.59
     partenza
    -0.58
     berço
    -0.57
    warp
    -0.57
     brancas
    -0.57
    POSITIVE LOGITS
     improv
    1.36
     Impro
    1.05
     payable
    1.02
     impro
    0.96
     improvis
    0.95
    impro
    0.89
     improvisation
    0.84
     Payable
    0.84
     workshop
    0.75
     workshops
    0.75
    Act Density 0.001%

    No Known Activations