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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and assess their frequency in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.10
    2:0.05
    3:0.05
    4:0.28
    5:0.05
    6:0.03
    7:0.16
    8:0.03
    9:0.03
    10:0.07
    11:0.05
    Negative Logits
     Learns
    -2.65
    uscript
    -2.51
    odcast
    -2.48
    tumblr
    -2.45
    externalActionCode
    -2.35
    isode
    -2.34
     earliest
    -2.33
     ourselves
    -2.33
    UTC
    -2.33
    ��
    -2.26
    POSITIVE LOGITS
    itaire
    2.72
    this
    2.39
     this
    2.36
    acha
    2.32
    isite
    2.30
    ño
    2.29
    ="#
    2.20
     bidder
    2.20
     This
    2.20
    itic
    2.19
    Act Density 0.006%

    No Known Activations