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

    Neuronpedia

    INDEX
    Explanations

    words related to criticism or evaluation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Boone
    -0.73
     machine
    -0.70
     Machine
    -0.66
     Alchemist
    -0.62
     paraly
    -0.62
    xus
    -0.61
     mater
    -0.60
     Patriarch
    -0.58
     Lizard
    -0.57
     Sapphire
    -0.57
    POSITIVE LOGITS
    ortun
    1.30
    ortunate
    1.29
    rozen
    1.29
    ruits
    1.28
    letcher
    1.24
    avour
    1.24
    avorable
    1.23
    raction
    1.23
    athom
    1.21
    ocusing
    1.21
    Act Density 1.581%

    No Known Activations