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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or conditional actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    conditional statements and expressions using "if" and "to" constructions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.80
    ंदीखरीदारी
    -0.80
    aarrggbb
    -0.68
     myſelf
    -0.67
     surla
    -0.65
    ]),
    -0.64
     Monfieur
    -0.61
     Мексичка
    -0.60
     Jefus
    -0.60
    Tembelea
    -0.58
    POSITIVE LOGITS
     melakukannya
    0.45
    有所
    0.45
     prevail
    0.44
     prevails
    0.39
     ensue
    0.37
     hacerlo
    0.36
     ensues
    0.36
     proceed
    0.35
     gjelder
    0.35
     oblige
    0.35
    Act Density 0.845%

    No Known Activations