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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal belongings or possessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.02
    2:0.06
    3:0.04
    4:0.04
    5:0.04
    6:0.46
    7:0.01
    8:0.05
    9:0.05
    10:0.04
    11:0.03
    Negative Logits
    glomer
    -1.31
     digestion
    -1.27
     Mobil
    -1.25
     avoidance
    -1.23
     sparing
    -1.20
     neutrality
    -1.20
     enrichment
    -1.15
     reflection
    -1.13
     Kitt
    -1.11
    lling
    -1.10
    POSITIVE LOGITS
    sic
    1.94
    trump
    1.52
    enario
    1.42
    ances
    1.41
    �
    1.40
     Marketable
    1.39
    ree
    1.37
    soDeliveryDate
    1.35
    ️
    1.32
    ufact
    1.32
    Act Density 0.628%

    No Known Activations