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

    Neuronpedia

    INDEX
    Explanations

    descriptions of defining features and characteristics of objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.67
     Urbano
    -0.66
     urbaine
    -0.65
     carbonic
    -0.65
    endpush
    -0.65
    SequentialGroup
    -0.63
    einander
    -0.63
    voices
    -0.61
    SPJ
    -0.61
     ordine
    -0.61
    POSITIVE LOGITS
     characteristics
    1.71
     traits
    1.46
     Characteristics
    1.42
    characteristics
    1.40
     characteristic
    1.38
    Characteristics
    1.31
     qualities
    1.26
     trait
    1.26
     properties
    1.23
     Traits
    1.23
    Act Density 0.321%

    No Known Activations