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

    Neuronpedia

    INDEX
    Explanations

    negations or words with the prefix "un."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sinne
    -0.48
    kit
    -0.37
     Hen
    -0.36
     Braut
    -0.36
    Kit
    -0.34
    Me
    -0.34
    볍
    -0.34
    ługi
    -0.33
    umumkan
    -0.33
    océan
    -0.33
    POSITIVE LOGITS
    */),
    0.60
    ]")]
    0.60
    Personendaten
    0.56
     getRule
    0.55
     InputDecoration
    0.54
    --}}
    0.54
    UnusedPrivate
    0.54
    }$​
    0.54
     BorderSide
    0.53
     Anſ
    0.52
    Act Density 0.353%

    No Known Activations