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

    Neuronpedia

    INDEX
    Explanations

    terms related to the act of removal or elimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IRMWARE
    -0.16
    wise
    -0.15
    uth
    -0.15
    umes
    -0.14
    rrha
    -0.14
    	Copyright
    -0.14
    rome
    -0.13
    oning
    -0.13
    ácil
    -0.13
    ume
    -0.13
    POSITIVE LOGITS
    /Add
    0.17
    /add
    0.16
    /change
    0.14
    able
    0.14
     substances
    0.14
    ocale
    0.14
    opoulos
    0.14
    gross
    0.14
    ضÛĮ
    0.14
    endum
    0.14
    Act Density 0.054%

    No Known Activations