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

    Neuronpedia

    INDEX
    Explanations

    terms related to educational or academic topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rade
    -0.72
    thood
    -0.71
     illustrates
    -0.68
    rage
    -0.66
    iffe
    -0.66
    tel
    -0.63
     understands
    -0.63
    sudo
    -0.62
     demonstrates
    -0.62
    adeon
    -0.62
    POSITIVE LOGITS
    oret
    1.37
     latter
    1.33
     hallmark
    1.16
     longest
    1.08
     same
    1.07
     oldest
    1.06
     simplest
    1.06
     smallest
    1.06
     earliest
    1.05
     easiest
    1.03
    Act Density 0.166%

    No Known Activations