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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships and connections in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.08
    3:0.06
    4:0.10
    5:0.04
    6:0.04
    7:0.26
    8:0.04
    9:0.05
    10:0.13
    11:0.08
    Negative Logits
     ritual
    -1.83
     Metatron
    -1.72
     trauma
    -1.72
     modesty
    -1.62
    jury
    -1.62
     traumat
    -1.61
     Ritual
    -1.57
     neglect
    -1.56
     grieving
    -1.51
     rituals
    -1.49
    POSITIVE LOGITS
    english
    2.11
    Company
    1.78
    Cola
    1.76
    Companies
    1.72
    enz
    1.68
    riger
    1.67
     Crossref
    1.66
    ibaba
    1.65
    BuyableInstoreAndOnline
    1.65
     avenue
    1.63
    Act Density 0.000%

    No Known Activations