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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating perception or suggestions of something being misleading or deceptive

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

    seem followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.59
    AddTagHelper
    -0.58
    elemField
    -0.58
    webElementXpaths
    -0.58
    GEBURTSDATUM
    -0.57
     Wikimedijinoj
    -0.56
    Personendaten
    -0.55
    writeFieldEnd
    -0.54
     Administrativna
    -0.53
    portál
    -0.53
    POSITIVE LOGITS
     but
    0.34
    wele
    0.32
    But
    0.32
    glBind
    0.30
    Vir
    0.29
    acao
    0.29
    ziare
    0.29
    breng
    0.28
     intérieure
    0.28
    Fra
    0.28
    Act Density 0.123%

    No Known Activations