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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "of" and possibly phrases indicating relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.07
    3:0.06
    4:0.13
    5:0.02
    6:0.05
    7:0.40
    8:0.03
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
    andise
    -1.91
    yne
    -1.70
    ioch
    -1.67
    potion
    -1.66
    arger
    -1.64
    channelAvailability
    -1.54
    aneously
    -1.54
    grown
    -1.53
    uid
    -1.52
     valued
    -1.50
    POSITIVE LOGITS
     heights
    1.65
     stunts
    1.53
     complications
    1.52
     pitfalls
    1.52
     interference
    1.52
     bullies
    1.51
     Cruel
    1.51
     stunt
    1.46
     consequences
    1.46
     surprises
    1.45
    Act Density 0.000%

    No Known Activations