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

    Neuronpedia

    INDEX
    Explanations

    mentions of events and performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behavior
    -0.16
    Startup
    -0.16
     specialized
    -0.16
    Defense
    -0.15
     behaviors
    -0.15
     personalized
    -0.15
     honors
    -0.15
    usz
    -0.14
    CENTER
    -0.14
    ashion
    -0.14
    POSITIVE LOGITS
     pant
    0.25
     transfers
    0.23
     Olivier
    0.22
     transfer
    0.21
     UK
    0.21
     transferred
    0.21
     Strict
    0.20
     Curve
    0.20
     transferring
    0.20
     sell
    0.20
    Act Density 0.027%

    No Known Activations