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

    Neuronpedia

    INDEX
    Explanations

    occurrences of first-person and second-person pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esser
    -0.17
    vrd
    -0.16
    imple
    -0.15
    è¡Ĩ
    -0.15
     ↵↵
    -0.15
    avec
    -0.15
     å¾Ĵ
    -0.14
    =Value
    -0.14
    oplayer
    -0.14
    iefs
    -0.14
    POSITIVE LOGITS
     receive
    0.24
     experience
    0.21
     receives
    0.20
     lose
    0.20
     experiences
    0.19
     Receive
    0.19
     get
    0.19
     find
    0.19
    LOSE
    0.19
     rece
    0.18
    Act Density 0.310%

    No Known Activations