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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific companies and individuals in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with personal achievements and confidence in project success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     virginity
    -0.84
    rape
    -0.79
     pretended
    -0.72
     punishments
    -0.71
    reply
    -0.70
    edit
    -0.68
     torture
    -0.68
    gery
    -0.65
    shit
    -0.65
     leftists
    -0.64
    POSITIVE LOGITS
     leveraging
    1.00
    "}],"
    0.97
     partnership
    0.96
     partnering
    0.96
     innovative
    0.90
     synerg
    0.90
    atform
    0.87
     collaborations
    0.87
     collaboration
    0.87
     accelerator
    0.87
    Act Density 0.838%

    No Known Activations