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

    Neuronpedia

    INDEX
    Explanations

    references to death and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upil
    -0.16
    ureka
    -0.16
    åĨĴ
    -0.16
    irut
    -0.16
    nech
    -0.15
    anela
    -0.15
    hma
    -0.14
    asto
    -0.14
    icky
    -0.14
     bloodstream
    -0.14
    POSITIVE LOGITS
     penalty
    0.36
    wish
    0.31
    bed
    0.31
     Penalty
    0.31
    ly
    0.30
     sentence
    0.30
    trap
    0.30
     toll
    0.30
     row
    0.28
    -row
    0.27
    Act Density 0.015%

    No Known Activations