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

    Neuronpedia

    INDEX
    Explanations

    words related to possessive pronouns and associated possessiveness in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     @@
    -0.69
     ire
    -0.62
    ILA
    -0.62
     votes
    -0.61
     covari
    -0.60
     accomplishments
    -0.59
     disapproval
    -0.58
     FAR
    -0.57
     indebted
    -0.57
     Choice
    -0.56
    POSITIVE LOGITS
    seat
    0.86
    chwitz
    0.80
    engine
    0.79
    wheel
    0.78
    chair
    0.77
    umbledore
    0.77
    tracks
    0.76
     groove
    0.75
    chairs
    0.74
     seat
    0.74
    Act Density 0.274%

    No Known Activations