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

    Neuronpedia

    INDEX
    Explanations

    the word "is" in various contexts, indicating states or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſtate
    -0.91
     ainfi
    -0.91
     ſche
    -0.88
    ſelves
    -0.88
     ſever
    -0.88
    aarrggbb
    -0.85
     Monfieur
    -0.84
     pleaſure
    -0.84
     faſt
    -0.82
     myſelf
    -0.82
    POSITIVE LOGITS
     is
    1.27
     was
    1.12
     can
    0.92
     has
    0.92
     were
    0.92
     are
    0.90
    is
    0.87
     in
    0.85
     and
    0.82
     of
    0.80
    Act Density 1.095%

    No Known Activations