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

    Neuronpedia

    INDEX
    Explanations

    specific references to relationships and marital statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tape
    -0.16
    ApplicationBuilder
    -0.16
    ãĤ¤ãĥī
    -0.16
    annya
    -0.15
    rubu
    -0.15
    nl
    -0.15
    river
    -0.15
    @nate
    -0.15
    WARE
    -0.15
    ODEV
    -0.15
    POSITIVE LOGITS
    ce
    0.42
    ces
    0.41
    ced
    0.39
    cing
    0.32
    se
    0.30
    ç
    0.30
    ça
    0.29
    CE
    0.28
    cers
    0.28
    cer
    0.28
    Act Density 0.069%

    No Known Activations