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

    Neuronpedia

    INDEX
    Explanations

    terms related to employment and job statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     general
    -0.53
    中でも
    -0.51
     strategies
    -0.49
    madre
    -0.49
     bio
    -0.48
    حديد
    -0.48
    rå
    -0.48
     control
    -0.47
    "?>
    -0.47
    hetta
    -0.46
    POSITIVE LOGITS
     fatalities
    0.83
    Deaths
    0.83
     deaths
    0.83
     Deaths
    0.81
     JOBS
    0.80
    Населення
    0.79
     calories
    0.75
     tonnage
    0.75
     Jobs
    0.75
     CreateTagHelper
    0.74
    Act Density 0.464%

    No Known Activations