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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with caloric content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.06
    2:0.09
    3:0.08
    4:0.08
    5:0.07
    6:0.08
    7:0.08
    8:0.07
    9:0.06
    10:0.10
    11:0.10
    Negative Logits
     specs
    -2.19
    terms
    -1.88
    Reviewer
    -1.87
     calculator
    -1.78
     ELECT
    -1.74
     "$:/
    -1.68
    Tax
    -1.67
     TEST
    -1.67
     BAS
    -1.66
     Accounting
    -1.63
    POSITIVE LOGITS
     Mecca
    1.82
     locality
    1.80
     drainage
    1.68
     cemetery
    1.66
     adjacent
    1.61
     Hole
    1.59
     isolated
    1.57
     wolves
    1.57
     ditch
    1.56
     Chinatown
    1.54
    Act Density 0.000%

    No Known Activations