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

    Neuronpedia

    INDEX
    Explanations

    words related to scientific topics and controversial issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases asserting the presence or importance of various issues, often contrasting them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Works
    -0.67
     Ends
    -0.67
     Believe
    -0.64
    ools
    -0.64
     Moines
    -0.63
     Janeiro
    -0.62
    sburg
    -0.62
     Supports
    -0.61
    ieves
    -0.61
     ACTIONS
    -0.60
    POSITIVE LOGITS
     poised
    1.05
    Reviewer
    1.02
     indispensable
    1.00
     arguably
    1.00
     prominently
    0.98
     intrinsically
    0.96
     insepar
    0.95
     synonymous
    0.95
     regarded
    0.93
     overshadowed
    0.93
    Act Density 0.485%

    No Known Activations