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

    Neuronpedia

    INDEX
    Explanations

    references to self and others in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     they
    -0.62
     we
    -0.58
    Cer
    -0.54
     he
    -0.53
    <h2>
    -0.52
     published
    -0.49
    ']").
    -0.49
    viana
    -0.48
    alyptus
    -0.48
     untersch
    -0.48
    POSITIVE LOGITS
    OGND
    0.90
    Him
    0.87
    Them
    0.86
     Them
    0.85
    Myself
    0.81
     Myself
    0.79
    Autoritní
    0.79
    myself
    0.78
    themselves
    0.78
     Him
    0.77
    Act Density 0.137%

    No Known Activations