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

    Neuronpedia

    INDEX
    Explanations

    phrases related to options, choices, or selection processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pre
    -0.48
     
    -0.46
    1
    -0.41
     E
    -0.41
    pre
    -0.40
     pré
    -0.40
    ()
    -0.40
    pr
    -0.40
     pr
    -0.39
     É
    -0.39
    POSITIVE LOGITS
     ujednoznacz
    1.16
     myſelf
    1.11
     purpoſe
    1.09
     themſelves
    1.05
     itſelf
    1.05
     Jefus
    1.03
     Theſe
    1.02
    +#+#
    1.01
     whoſe
    0.97
     himſelf
    0.96
    Act Density 1.009%

    No Known Activations