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

    Neuronpedia

    INDEX
    Explanations

    references to development and progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.83
    xual
    -0.81
     Moonlight
    -0.73
     Rouge
    -0.69
     Twain
    -0.67
    ocene
    -0.67
     Objective
    -0.66
    ahead
    -0.64
    SHIP
    -0.62
    tone
    -0.62
    POSITIVE LOGITS
    olved
    1.39
    irtual
    1.33
    olve
    1.30
    iating
    1.28
    iant
    1.28
    iates
    1.27
    olution
    1.26
    iated
    1.26
    iants
    1.24
    iate
    1.18
    Act Density 0.004%

    No Known Activations