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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rumors, myths, and popular notions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    semble
    -0.65
     Occupations
    -0.64
    pex
    -0.63
     Pradesh
    -0.62
    omez
    -0.62
    iencies
    -0.62
    loads
    -0.61
    keys
    -0.60
    dos
    -0.60
    usalem
    -0.59
    POSITIVE LOGITS
     regarding
    0.90
     floated
    0.78
     expressed
    0.77
    ually
    0.77
     concerning
    0.76
     horr
    0.75
     about
    0.75
     conveyed
    0.74
     moot
    0.73
     entertained
    0.72
    Act Density 2.274%

    No Known Activations