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

    Neuronpedia

    INDEX
    Explanations

    references to suicide and self-sacrifice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sơ
    -0.15
    ç«¥
    -0.14
    irim
    -0.14
     olan
    -0.14
    esses
    -0.14
    å¾Ħ
    -0.14
    .om
    -0.14
     TLC
    -0.13
    needle
    -0.13
    .getNum
    -0.13
    POSITIVE LOGITS
     dying
    0.18
     death
    0.16
     die
    0.15
     Fuse
    0.15
     chance
    0.15
     died
    0.14
    oval
    0.14
     Cooper
    0.14
    LO
    0.13
     DIE
    0.13
    Act Density 0.199%

    No Known Activations