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

    Neuronpedia

    INDEX
    Explanations

    legal terms and policies related to online content regulation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the conjunction 'or'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pony
    -0.72
     Roose
    -0.72
    onday
    -0.72
    ocracy
    -0.71
    NOW
    -0.69
    ires
    -0.67
    istors
    -0.66
     Loren
    -0.65
    aturday
    -0.63
     Uriel
    -0.62
    POSITIVE LOGITS
    acle
    1.32
    chard
    1.23
    acles
    1.21
    ifice
    1.20
     otherwise
    1.16
    Else
    1.10
    chid
    1.08
    nam
    1.03
     alternatively
    0.98
    GAN
    0.96
    Act Density 0.161%

    No Known Activations