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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions and modifications

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    listed
    -0.69
     misled
    -0.67
    awar
    -0.64
    enery
    -0.64
    nor
    -0.63
    DOWN
    -0.62
     toured
    -0.61
    wordpress
    -0.61
    grain
    -0.60
    ice
    -0.60
    POSITIVE LOGITS
    livion
    0.92
     manageable
    0.88
     accommodate
    0.83
     simpler
    0.81
    othy
    0.75
     mush
    0.75
     something
    0.73
     safer
    0.72
     adulthood
    0.69
     resemble
    0.66
    Act Density 2.419%

    No Known Activations