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

    Neuronpedia

    INDEX
    Explanations

    phrases that express opinions or judgments related to design and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jspb
    -0.57
    Personendaten
    -0.48
    الي
    -0.47
     autorytatywna
    -0.45
    sunter
    -0.45
     foglal
    -0.44
    TagMode
    -0.42
     kaya
    -0.42
    istia
    -0.41
    MessageInfo
    -0.41
    POSITIVE LOGITS
     understatement
    0.76
    という言葉
    0.73
     term
    0.72
    term
    0.71
     Term
    0.69
    Term
    0.69
     adjectives
    0.68
    terms
    0.65
     termen
    0.63
    FTFY
    0.62
    Act Density 0.178%

    No Known Activations