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

    Neuronpedia

    INDEX
    Explanations

    references to death

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    олож
    -0.14
    opus
    -0.14
    Ñĩин
    -0.14
    mesinin
    -0.14
    -setting
    -0.14
    olph
    -0.14
    vented
    -0.14
    ãģ¾ãģ¾
    -0.14
    tems
    -0.14
    aping
    -0.13
    POSITIVE LOGITS
    bed
    0.20
     thro
    0.19
     penalty
    0.19
    oscope
    0.17
    death
    0.17
    ened
    0.17
    iez
    0.17
    -death
    0.16
     Penalty
    0.16
    fully
    0.16
    Act Density 0.018%

    No Known Activations