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

    Neuronpedia

    INDEX
    Explanations

    phrases and quantifiers related to time and frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.12
    3:0.05
    4:0.37
    5:0.02
    6:0.08
    7:0.05
    8:0.04
    9:0.03
    10:0.08
    11:0.07
    Negative Logits
    represented
    -1.67
    existence
    -1.61
    iage
    -1.48
    edom
    -1.47
    rollment
    -1.43
    oka
    -1.43
    rious
    -1.40
    orer
    -1.35
    oppable
    -1.32
    metadata
    -1.28
    POSITIVE LOGITS
     horm
    1.99
     wisely
    1.55
     wink
    1.54
    Laughs
    1.50
     disguise
    1.49
    ��
    1.46
     istg
    1.43
     anyway
    1.43
     accordingly
    1.42
     beforehand
    1.41
    Act Density 0.160%

    No Known Activations