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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylon
    -0.17
    armor
    -0.15
    arton
    -0.14
    ceiver
    -0.14
    //{{
    -0.14
     skl
    -0.14
    ihn
    -0.14
    /animate
    -0.14
    uche
    -0.14
    .IsActive
    -0.14
    POSITIVE LOGITS
     trying
    0.24
     bas
    0.23
     operating
    0.18
     correct
    0.18
     following
    0.17
     TRY
    0.17
    ãĥ³ãĥĨãĤ£
    0.17
     try
    0.17
     merely
    0.17
     saying
    0.17
    Act Density 0.137%

    No Known Activations