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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions taken by people or groups of people

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilty
    -0.75
    wow
    -0.69
    orage
    -0.66
    Iv
    -0.66
    Reading
    -0.64
    aha
    -0.64
    ieth
    -0.64
    window
    -0.63
    avorable
    -0.63
    YS
    -0.63
    POSITIVE LOGITS
     resorted
    1.18
     devised
    0.97
     decided
    0.86
     resort
    0.84
     recourse
    0.83
     opted
    0.82
     resorts
    0.82
    pmwiki
    0.80
     devise
    0.77
     undertook
    0.76
    Act Density 0.886%

    No Known Activations