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

    Neuronpedia

    INDEX
    Explanations

    actions related to scientific research or experimentation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.71
     виправивши
    -0.70
    NameInMap
    -0.67
     greateſt
    -0.63
    ſelf
    -0.63
     loue
    -0.63
    日閲覧
    -0.62
     auroit
    -0.61
     وصلة
    -0.60
    RectangleBorder
    -0.59
    POSITIVE LOGITS
    </em>
    0.54
    myself
    0.48
     c
    0.47
    мента
    0.46
     sem
    0.45
    </h3>
    0.45
    </i>
    0.44
    </blockquote>
    0.44
     si
    0.44
     l
    0.44
    Act Density 0.334%

    No Known Activations