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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to first-hand experiences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    arter
    -0.81
    ramid
    -0.74
    phis
    -0.73
    oleon
    -0.73
    issa
    -0.73
    itary
    -0.72
    pty
    -0.72
    prime
    -0.71
     Puzzle
    -0.69
    yip
    -0.69
    POSITIVE LOGITS
     knowledge
    0.94
     testimonies
    0.93
     firsthand
    0.91
     experience
    0.90
     testimony
    0.88
     witness
    0.87
     experiences
    0.86
     witnessing
    0.86
    Witness
    0.86
     eyewitness
    0.84
    Act Density 0.026%

    No Known Activations