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

    Neuronpedia

    INDEX
    Explanations

    questions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    robe
    -0.65
    lich
    -0.63
     favor
    -0.62
    ulic
    -0.61
    ster
    -0.59
    enburg
    -0.58
    MER
    -0.58
    por
    -0.57
    enberg
    -0.57
    uttering
    -0.56
    POSITIVE LOGITS
    soever
    1.41
     happens
    1.40
     happened
    1.35
     transpired
    1.24
     constitutes
    1.13
     happ
    1.12
     else
    1.07
     distinguishes
    0.99
     redes
    0.96
     kinds
    0.96
    Act Density 1.161%

    No Known Activations