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

    Neuronpedia

    INDEX
    Explanations

    titles or labels

    oai_token-act-pair · gpt-3.5-turbo

    titles and themes related to anonymity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Schwarz
    -0.71
     Coulter
    -0.64
    OTT
    -0.63
    ada
    -0.63
    Albert
    -0.61
    ++++++++++++++++
    -0.61
    âĺ
    -0.59
     Sutherland
    -0.59
     Orn
    -0.58
     Salem
    -0.57
    POSITIVE LOGITS
    itled
    1.45
    ness
    0.96
    selves
    0.89
    nesses
    0.88
    ebted
    0.86
    leness
    0.84
    ignty
    0.83
    xual
    0.83
    ividual
    0.82
    soever
    0.80
    Act Density 0.009%

    No Known Activations