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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social media activism and hashtags

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social media movements and campaigns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     warranties
    -0.76
     reins
    -0.67
     capacities
    -0.66
     warranty
    -0.65
     Forge
    -0.65
     inspectors
    -0.64
     nineteen
    -0.64
     exhaustive
    -0.63
     faculties
    -0.63
     margins
    -0.62
    POSITIVE LOGITS
    _.
    1.00
    _(
    0.99
    _
    0.96
    __
    0.93
    Fail
    0.93
    Jew
    0.90
    WithNo
    0.87
    JD
    0.84
    2020
    0.83
    pic
    0.83
    Act Density 0.105%

    No Known Activations