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

    Neuronpedia

    INDEX
    Explanations

    The main thing this neuron does is find words related to consequences or outcomes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    sites
    -0.68
     Ribbon
    -0.63
     Robo
    -0.60
    pload
    -0.58
     Fired
    -0.58
     Sau
    -0.58
     voic
    -0.58
    mbuds
    -0.57
     Spoon
    -0.57
     Scholars
    -0.56
    POSITIVE LOGITS
     thereof
    1.19
     of
    0.91
    ainer
    0.76
    iveness
    0.74
    OF
    0.71
    growth
    0.70
    of
    0.70
    ivity
    0.67
     stemming
    0.67
    ively
    0.65
    Act Density 0.038%

    No Known Activations