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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating death or mortality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     charge
    -0.16
    jets
    -0.15
    amar
    -0.15
     dc
    -0.15
     å£
    -0.15
    ãĥ³
    -0.15
    adera
    -0.15
     strong
    -0.15
    indow
    -0.14
     rat
    -0.14
    POSITIVE LOGITS
    avity
    0.16
    .WinForms
    0.15
     reluct
    0.14
    edis
    0.14
    erus
    0.14
     Ston
    0.14
    trap
    0.14
    -inline
    0.13
     Sting
    0.13
    ÏħÏĢ
    0.13
    Act Density 0.009%

    No Known Activations