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

    Neuronpedia

    INDEX
    Explanations

    discussion about participation and contributions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.77
     "..\..\
    -0.76
     "..\..\..\
    -0.75
    ########.
    -0.68
     Real
    -0.67
     the
    -0.66
     a
    -0.65
     real
    -0.64
    '}}
    -0.62
     ***!
    -0.61
    POSITIVE LOGITS
     myſelf
    0.96
     répondu
    0.85
     becauſe
    0.85
     interact
    0.84
     Participate
    0.82
     interacts
    0.80
     itſelf
    0.80
    interact
    0.79
     berdua
    0.77
     competir
    0.76
    Act Density 0.489%

    No Known Activations