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

    Neuronpedia

    INDEX
    Explanations

    conjunctions, particularly the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.08
    3:0.08
    4:0.07
    5:0.08
    6:0.07
    7:0.10
    8:0.07
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
    repre
    -2.60
     crochet
    -2.57
    jew
    -2.57
     srfAttach
    -2.55
    ube
    -2.54
    roman
    -2.50
    gew
    -2.48
     Parm
    -2.48
    plant
    -2.42
     cutter
    -2.35
    POSITIVE LOGITS
    SPONSORED
    3.16
     peaked
    2.85
     commenced
    2.71
     Vale
    2.56
     Rising
    2.46
     Firstly
    2.41
     anecd
    2.36
    ,[
    2.33
     existed
    2.33
     Quarterly
    2.30
    Act Density 0.000%

    No Known Activations