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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial interests and ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lay
    -0.50
     stay
    -0.48
    Wel
    -0.47
     set
    -0.47
    belec
    -0.46
     hired
    -0.46
     bom
    -0.46
     fell
    -0.45
     verk
    -0.44
     plan
    -0.44
    POSITIVE LOGITS
     interest
    1.88
    interest
    1.80
     Interest
    1.73
    Interest
    1.68
     interests
    1.57
     INTEREST
    1.56
     Interests
    1.50
    interests
    1.46
    INTEREST
    1.36
     متعلقه
    1.27
    Act Density 0.215%

    No Known Activations