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

    Neuronpedia

    INDEX
    Explanations

    personal experiences or memories

    oai_token-act-pair · gpt-3.5-turbo

    the personal pronoun "I" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.74
    advertisement
    -0.70
    pires
    -0.65
    auga
    -0.64
    farious
    -0.64
    ä¹ĭ
    -0.63
    Allows
    -0.61
    éļ
    -0.61
     applause
    -0.61
     assertions
    -0.59
    POSITIVE LOGITS
    'm
    1.22
    've
    1.20
     remember
    1.13
     grew
    1.11
     lived
    1.10
     graduated
    1.08
     dunno
    1.04
    'd
    1.02
     guess
    0.98
     suppose
    0.98
    Act Density 0.183%

    No Known Activations