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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political criticisms and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Becoming
    -0.53
     becoming
    -0.51
    NameInMap
    -0.48
    hyrchwyd
    -0.45
     become
    -0.45
    >//
    -0.45
    becoming
    -0.43
     Becoming
    -0.42
     })
    -0.41
     Th
    -0.40
    POSITIVE LOGITS
    MethodManager
    0.87
    contentLoaded
    0.79
     <<<<<<<<<<<<<<
    0.72
     autorytatywna
    0.72
    ArrowToggle
    0.70
     ©️
    0.69
    enterOuterAlt
    0.67
    setVerticalGroup
    0.66
    Personendaten
    0.65
    Демографія
    0.65
    Act Density 0.065%

    No Known Activations