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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating agreements or consent in discussions

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

    agreed to perform actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     currentUser
    -0.45
    BrowserModule
    -0.44
     Fuentes
    -0.43
     Far
    -0.42
     Stur
    -0.41
     DB
    -0.40
     kasarigan
    -0.40
    Portail
    -0.39
    CacheManager
    -0.39
    mailer
    -0.39
    POSITIVE LOGITS
    WriteTagHelper
    0.75
    OGND
    0.60
    .*")]
    0.58
     agreed
    0.56
    ########.
    0.56
    agreed
    0.52
     promised
    0.52
    ucchini
    0.52
    adaptiveStyles
    0.51
    +#+
    0.50
    Act Density 0.013%

    No Known Activations