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

    Neuronpedia

    INDEX
    Explanations

    information about a person's background and life events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.57
    ⓧ
    -0.97
    <?
    -0.83
    /**
    -0.76
    
    -0.73
     continue
    -0.71
    /*
    -0.70
     got
    -0.67
     put
    -0.67
     strive
    -0.67
    POSITIVE LOGITS
     soulign
    1.89
     Juf
    1.82
     vété
    1.75
     véhic
    1.73
     Keny
    1.65
     écout
    1.64
     délib
    1.62
     accla
    1.57
     clô
    1.57
     considér
    1.55
    Act Density 2.350%

    No Known Activations