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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "you" and related personal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     è£ıç
    -0.90
     è£ıè
    -0.82
     Additional
    -0.72
    âģ
    -0.72
     Mehran
    -0.71
    ollower
    -0.67
    Effective
    -0.66
     Luxem
    -0.63
    ä¹ĭ
    -0.63
     è£ı
    -0.63
    POSITIVE LOGITS
     kinda
    1.48
     gotta
    1.42
     dunno
    1.37
     wanna
    1.27
     definitely
    1.21
     REALLY
    1.16
     probably
    1.10
    've
    1.08
    'll
    1.08
    'd
    1.07
    Act Density 0.382%

    No Known Activations