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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns in relation to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.05
    2:0.08
    3:0.08
    4:0.07
    5:0.09
    6:0.06
    7:0.07
    8:0.09
    9:0.09
    10:0.09
    11:0.09
    Negative Logits
     Bere
    -1.79
     ninety
    -1.67
     Solitaire
    -1.60
     eighty
    -1.59
     downed
    -1.55
     fifty
    -1.50
     vigilance
    -1.48
     sixty
    -1.46
     occupancy
    -1.44
    renheit
    -1.42
    POSITIVE LOGITS
    artney
    1.80
    UTERS
    1.72
    IVERS
    1.70
    ilk
    1.70
    ゴン
    1.68
     sidx
    1.66
    merce
    1.57
    魔
    1.55
    ktop
    1.53
    ourke
    1.53
    Act Density 0.000%

    No Known Activations