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

    Neuronpedia

    INDEX
    Explanations

    words related to defining characteristics and features of objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Urbano
    -0.68
     Diversion
    -0.62
    einander
    -0.61
    junge
    -0.61
    /</
    -0.61
    handleClick
    -0.61
     cerebro
    -0.60
     egress
    -0.60
     helico
    -0.60
    jButton
    -0.60
    POSITIVE LOGITS
     characteristics
    1.56
     characteristic
    1.42
     traits
    1.33
    characteristics
    1.33
     Characteristics
    1.30
    Characteristics
    1.22
     Characteristic
    1.22
    characteristic
    1.17
    Characteristic
    1.14
     CHARACTERISTICS
    1.13
    Act Density 0.323%

    No Known Activations