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

    Neuronpedia

    INDEX
    Explanations

    concepts related to personal experiences or reflections

    oai_token-act-pair · gpt-3.5-turbo

    themes related to personal sacrifice and individual experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Guan
    -0.69
     Brady
    -0.68
     Samar
    -0.66
    ©¶æ
    -0.64
    atton
    -0.61
     McDonnell
    -0.61
     Tycoon
    -0.60
    eria
    -0.60
     Nose
    -0.59
    ertodd
    -0.58
    POSITIVE LOGITS
     selves
    1.43
     counterparts
    1.27
     brethren
    0.83
     tongues
    0.77
    respective
    0.76
    selves
    0.73
     asses
    0.73
     histories
    0.72
     respective
    0.71
     holdings
    0.70
    Act Density 0.384%

    No Known Activations