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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and questions about the subject or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enthal
    -0.16
    uis
    -0.15
    odus
    -0.15
     ÑģÑĤанÑĥ
    -0.15
     Dah
    -0.15
    enge
    -0.14
    lein
    -0.14
    .gf
    -0.14
     Aren
    -0.14
     Duch
    -0.14
    POSITIVE LOGITS
     does
    0.57
    does
    0.45
     Does
    0.43
     did
    0.41
     do
    0.41
    Does
    0.40
    _does
    0.35
     DOES
    0.33
     doe
    0.31
    did
    0.30
    Act Density 0.115%

    No Known Activations