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

    Neuronpedia

    INDEX
    Explanations

    themes related to societal issues and criticisms of government and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     genuinely
    -0.16
    WithDuration
    -0.15
     âĺĨ
    -0.14
    ytt
    -0.14
    .codehaus
    -0.14
    iones
    -0.14
    chw
    -0.14
     вдÑĢÑĥг
    -0.13
    isini
    -0.13
    reative
    -0.13
    POSITIVE LOGITS
     necessarily
    0.46
     automatically
    0.46
     naturally
    0.45
    å¿ħ
    0.39
     automatic
    0.35
     inevitable
    0.34
     Naturally
    0.33
     inev
    0.32
     natural
    0.30
     Automatically
    0.30
    Act Density 0.624%

    No Known Activations