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

    Neuronpedia

    INDEX
    Explanations

    actions and terms related to manipulation or subterfuge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sterious
    -0.73
    InstanceState
    -0.67
    ignty
    -0.67
    idiary
    -0.61
    ollectionView
    -0.61
    ñola
    -0.60
     ostavi
    -0.59
    MMdd
    -0.58
     Steven
    -0.58
     stick
    -0.58
    POSITIVE LOGITS
    Rüyada
    0.81
     bailando
    0.68
     inspecting
    0.65
     murdered
    0.64
     murdering
    0.63
     conclure
    0.63
     suing
    0.62
     ziua
    0.62
     çünkü
    0.61
    ("]");
    0.61
    Act Density 1.055%

    No Known Activations