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

    Neuronpedia

    INDEX
    Explanations

    phrases related to removal or elimination

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.96
    /***
    -0.82
     intersper
    -0.73
     endow
    -0.67
    //*/
    -0.66
    
    -0.66
     strove
    -0.65
     amass
    -0.65
     rehabilitate
    -0.64
     overcrow
    -0.62
    POSITIVE LOGITS
     kram
    1.07
     lele
    1.06
     saar
    1.05
     meis
    1.05
     seksi
    1.01
     maksi
    1.01
     keramik
    1.01
     plak
    1.01
     nomine
    1.00
     ananas
    0.99
    Act Density 0.235%

    No Known Activations