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

    Neuronpedia

    INDEX
    Explanations

    phrases and context related to background information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.05
    3:0.05
    4:0.09
    5:0.02
    6:0.02
    7:0.50
    8:0.02
    9:0.02
    10:0.07
    11:0.07
    Negative Logits
    �
    -1.58
     divid
    -1.45
     paws
    -1.45
    fits
    -1.43
    bands
    -1.43
    oy
    -1.41
    stretched
    -1.41
    phies
    -1.40
    houses
    -1.40
    array
    -1.38
    POSITIVE LOGITS
     researching
    1.66
     Alchemist
    1.61
     Philosophy
    1.55
    cius
    1.52
     sourcing
    1.51
     biology
    1.51
     causation
    1.49
     resear
    1.47
     basics
    1.47
     researched
    1.45
    Act Density 0.009%

    No Known Activations