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

    Neuronpedia

    INDEX
    Explanations

    biological terms related to genes and their variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     q
    -0.55
     pem
    -0.52
     f
    -0.52
     d
    -0.51
     h
    -0.50
     je
    -0.50
     y
    -0.50
     u
    -0.48
     s
    -0.48
     j
    -0.47
    POSITIVE LOGITS
     myſelf
    1.33
     itſelf
    1.32
     themſelves
    1.20
     Monfieur
    1.18
    ſelf
    1.13
     himſelf
    1.10
     ―――――
    1.09
     Majefty
    1.08
     Efq
    1.07
     Jefus
    1.06
    Act Density 0.180%

    No Known Activations