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

    Neuronpedia

    INDEX
    Explanations

    present tense verbs ending in 'live'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.80
    /***
    -0.77
    
    -0.77
    /**
    -0.74
    ⓧ
    -0.72
    <?
    -0.72
    /*
    -0.71
    else
    -0.67
    hline
    -0.66
    HasColumnType
    -0.66
    POSITIVE LOGITS
     affor
    2.17
     maneu
    2.14
     impra
    2.11
     increa
    2.00
     accla
    1.90
     strick
    1.85
     emphat
    1.85
     inev
    1.85
     reluct
    1.81
     disagre
    1.79
    Act Density 0.098%

    No Known Activations