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

    Neuronpedia

    INDEX
    Explanations

    concepts related to economic fairness and taxation policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    visor
    -0.16
     burnt
    -0.16
    islav
    -0.16
     Vs
    -0.15
    loh
    -0.15
     seperate
    -0.14
     dept
    -0.14
     void
    -0.14
     negro
    -0.14
     Decor
    -0.14
    POSITIVE LOGITS
     analy
    0.19
     purpos
    0.18
     norm
    0.18
     Tradable
    0.17
     array
    0.17
     regime
    0.17
     policym
    0.16
     arrays
    0.16
    rough
    0.15
     disag
    0.15
    Act Density 0.523%

    No Known Activations