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

    Neuronpedia

    INDEX
    Explanations

    descriptive terms related to packaging and presentation quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.07
    2:0.03
    3:0.07
    4:0.04
    5:0.27
    6:0.05
    7:0.04
    8:0.18
    9:0.06
    10:0.02
    11:0.05
    Negative Logits
    heat
    -1.91
    athi
    -1.85
    regular
    -1.80
    Recently
    -1.78
    nesday
    -1.77
    Cooldown
    -1.77
     frequent
    -1.73
     Recently
    -1.71
    cipline
    -1.70
    arning
    -1.70
    POSITIVE LOGITS
     exhib
    1.88
     incrim
    1.85
     redacted
    1.84
     backstage
    1.79
     Patent
    1.79
    advertising
    1.77
     Podesta
    1.76
    SPONSORED
    1.76
     encaps
    1.74
     WARRANT
    1.71
    Act Density 0.001%

    No Known Activations