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

    Neuronpedia

    INDEX
    Explanations

    phrases related to declining comments or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UserScript
    -0.59
    correctly
    -0.59
     internetowa
    -0.58
    fjspx
    -0.54
    Успе
    -0.52
     parcialmente
    -0.50
     politely
    -0.50
     posib
    -0.50
    blurRadius
    -0.49
     possibili
    -0.48
    POSITIVE LOGITS
     comment
    0.75
     Comment
    0.71
     commenting
    0.71
     formally
    0.67
     specific
    0.65
     definitive
    0.64
     official
    0.62
     COMMENT
    0.62
    specific
    0.61
     conclusive
    0.61
    Act Density 0.630%

    No Known Activations