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

    Neuronpedia

    INDEX
    Explanations

    names of family members, especially siblings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.77
    ⓧ
    -0.74
    
    -0.73
    /*
    -0.70
    <?
    -0.69
    Kontrola
    -0.67
    oredCriteria
    -0.65
    intios
    -0.63
    <?
    -0.63
    maxcdn
    -0.63
    POSITIVE LOGITS
     Juf
    1.46
     affor
    1.40
     fortn
    1.35
     increa
    1.33
     maneu
    1.32
     unden
    1.32
     aen
    1.29
     sovere
    1.28
     Khart
    1.28
     stockholm
    1.27
    Act Density 0.116%

    No Known Activations