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

    Neuronpedia

    INDEX
    Explanations

    technical terms and product descriptions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rd
    -1.13
    achu
    -0.96
    enegger
    -0.96
    alez
    -0.94
    acus
    -0.84
    ness
    -0.83
    nesses
    -0.81
    rament
    -0.81
    eful
    -0.80
    otle
    -0.78
    POSITIVE LOGITS
     livest
    0.84
    soever
    0.78
     membrane
    0.67
     resp
    0.65
     thirds
    0.64
     bapt
    0.63
    poke
    0.60
    BILITIES
    0.59
     dipping
    0.59
     weep
    0.58
    Act Density 0.095%

    No Known Activations