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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and references to individuals' experiences and backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    หม
    -0.18
    iams
    -0.16
    å®ħ
    -0.15
    beth
    -0.14
     consequence
    -0.14
    apesh
    -0.14
     íĭ
    -0.14
    ouncements
    -0.14
     Boom
    -0.14
    icture
    -0.14
    POSITIVE LOGITS
     experiences
    0.37
     experience
    0.34
     thoughts
    0.26
     journey
    0.25
     impressions
    0.25
    periences
    0.23
    experience
    0.22
     favorite
    0.22
     reasons
    0.21
     reaction
    0.21
    Act Density 0.104%

    No Known Activations