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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "possession."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    byshev
    -0.66
     crime
    -0.57
     []:
    -0.53
     uska
    -0.52
     Davis
    -0.51
     Crime
    -0.51
     re
    -0.51
    crime
    -0.51
    AddHtmlAttribute
    -0.50
     statements
    -0.49
    POSITIVE LOGITS
    temp
    1.15
    ctions
    1.11
    ction
    1.00
     poffe
    0.95
     possession
    0.89
    cting
    0.84
     tartalomajánló
    0.80
     fhew
    0.80
    cted
    0.79
    ctive
    0.77
    Act Density 0.116%

    No Known Activations