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

    Neuronpedia

    INDEX
    Explanations

    terms associated with anti-properties, particularly in scientific or medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rujuakan
    -0.45
    UnusedPrivate
    -0.42
     escond
    -0.42
    ChrTalk
    -0.41
     sisa
    -0.39
    oneofs
    -0.39
     joka
    -0.39
     Abweich
    -0.38
    setVerticalGroup
    -0.38
     esconde
    -0.38
    POSITIVE LOGITS
     lip
    0.76
    anti
    0.65
     anti
    0.64
     Trim
    0.63
    endpoint
    0.62
     endpoint
    0.61
     Endpoint
    0.61
     InputDecoration
    0.60
     trim
    0.60
    trim
    0.56
    Act Density 0.290%

    No Known Activations