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

    Neuronpedia

    INDEX
    Explanations

    narrative structures and moments of realization or reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſeveral
    -0.80
     ſever
    -0.75
     myſelf
    -0.74
    ſelves
    -0.73
     Conſ
    -0.73
     leſs
    -0.73
     himſelf
    -0.72
     ſtate
    -0.72
     Cæsar
    -0.67
     itſelf
    -0.67
    POSITIVE LOGITS
     when
    0.96
    when
    0.80
     quando
    0.74
     later
    0.72
     gdy
    0.69
     när
    0.69
     cuando
    0.67
     When
    0.66
     khi
    0.66
     after
    0.63
    Act Density 0.229%

    No Known Activations