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

    Neuronpedia

    INDEX
    Explanations

    key terms related to legal cases and formal documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ysa
    -0.15
    оÑĢоÑĪ
    -0.14
    azen
    -0.14
    quine
    -0.14
    aucoup
    -0.14
     pÅĻitom
    -0.14
    erras
    -0.14
    ÑĤÑĢон
    -0.14
    ouden
    -0.14
    uzey
    -0.14
    POSITIVE LOGITS
     alongside
    1.02
     together
    0.88
     junto
    0.83
     along
    0.83
    along
    0.76
     Together
    0.68
    Together
    0.65
     вмеÑģÑĤе
    0.64
     Along
    0.63
     zusammen
    0.60
    Act Density 0.507%

    No Known Activations