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

    Neuronpedia

    INDEX
    Explanations

    mention of fossil fuels and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.05
    3:0.05
    4:0.06
    5:0.03
    6:0.19
    7:0.26
    8:0.03
    9:0.03
    10:0.16
    11:0.05
    Negative Logits
    �
    -2.18
    @@@@@@@@
    -1.88
    @@@@
    -1.88
    ━
    -1.86
    Interstitial
    -1.84
    �
    -1.82
    pport
    -1.82
    ═
    -1.55
     bye
    -1.54
    arez
    -1.53
    POSITIVE LOGITS
     Foss
    2.47
     fossil
    2.25
     fossils
    2.11
     physicist
    1.81
     geological
    1.80
    icist
    1.77
     astronomer
    1.73
     Astron
    1.68
     algae
    1.67
    wegian
    1.64
    Act Density 0.000%

    No Known Activations