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

    Neuronpedia

    INDEX
    Explanations

    references to the second person pronoun "you."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adolesc
    -0.67
    hander
    -0.65
    pires
    -0.60
    frames
    -0.59
    forms
    -0.57
    grades
    -0.56
    plates
    -0.56
    stellar
    -0.55
    Marginal
    -0.55
     purs
    -0.55
    POSITIVE LOGITS
    're
    1.03
    asel
    0.91
    've
    0.85
    imar
    0.83
     expire
    0.81
     are
    0.79
    atars
    0.78
     aren
    0.78
     underestimate
    0.77
     disapprove
    0.77
    Act Density 0.233%

    No Known Activations