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

    Neuronpedia

    INDEX
    Explanations

    phrases related to skepticism and the reliability of information

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

    doubt and trust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.69
    SourceChecksum
    -0.48
    HostException
    -0.47
    XmlAccessorType
    -0.45
     transférez
    -0.41
    Tē
    -0.41
    PropertyChanging
    -0.41
    RTEE
    -0.40
    prefixer
    -0.40
    atshirt
    -0.40
    POSITIVE LOGITS
     unreliable
    0.43
     anything
    0.40
     exaggerating
    0.39
     Wild
    0.39
    Халык
    0.38
    Искәрмәләр
    0.37
    InitStruct
    0.37
    靠
    0.36
    clearTimeout
    0.36
     مُعرِّف
    0.36
    Act Density 0.042%

    No Known Activations