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

    Neuronpedia

    INDEX
    Explanations

    questions and phrases indicating inquiries about actions or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     appunto
    -0.60
     totiž
    -0.57
    fanfic
    -0.57
     -,
    -0.56
     tartalomajánló
    -0.56
    HideInInspector
    -0.55
    Życiorys
    -0.55
     acestei
    -0.55
    rouvez
    -0.55
    /*
    -0.55
    POSITIVE LOGITS
    </h2>
    1.49
    </h3>
    1.31
    </h4>
    1.30
    </strong>
    1.27
    </h5>
    1.20
    </h1>
    1.14
    </b>
    1.14
    )$}
    1.10
    }$}
    1.10
    </h6>
    1.04
    Act Density 0.403%

    No Known Activations