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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and verbs indicating personal experiences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Endnotes
    -0.65
    IsContent
    -0.63
     المثال
    -0.59
    SequentialGroup
    -0.57
    agami
    -0.52
    DockStyle
    -0.52
     IANS
    -0.52
    nissen
    -0.49
    gegangen
    -0.47
    脚注の使い方
    -0.46
    POSITIVE LOGITS
     pleaſure
    0.75
     anſ
    0.75
     juſ
    0.74
     cauſe
    0.71
     Efq
    0.69
     ſen
    0.69
     Jefus
    0.69
     juſt
    0.66
     ſame
    0.65
     reaſon
    0.65
    Act Density 0.066%

    No Known Activations