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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the sharing or provision of information

    oai_token-act-pair · gpt-3.5-turbo

    instances of providing information or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enment
    -0.68
     interfered
    -0.68
     affair
    -0.67
    gain
    -0.66
    destruct
    -0.66
    roying
    -0.62
    land
    -0.61
    bec
    -0.61
    shore
    -0.60
    âĻ¥
    -0.60
    POSITIVE LOGITS
     details
    1.10
     detailed
    1.09
     insight
    1.02
     specifics
    0.99
     assurances
    0.99
     clarification
    0.96
     examples
    0.95
     testimony
    0.93
     insights
    0.93
     suggestions
    0.92
    Act Density 0.105%

    No Known Activations