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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relational or possessive structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    czer
    -0.49
     She
    -0.48
    bnf
    -0.45
    Distribuzione
    -0.44
    chila
    -0.43
    ément
    -0.43
     she
    -0.42
    JspWriter
    -0.41
     toneladas
    -0.41
     iyo
    -0.41
    POSITIVE LOGITS
    بوابة
    0.81
     مشين
    0.77
     Bioaccumulative
    0.70
     colorWith
    0.67
     relevance
    0.66
    ')));
    0.66
    }{*}{}
    0.66
    initializeApp
    0.65
    lorette
    0.65
    gestone
    0.65
    Act Density 0.381%

    No Known Activations