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

    Neuronpedia

    INDEX
    Explanations

    words related to power or authority

    oai_token-act-pair · gpt-3.5-turbo

    words or terms associated with religious or spiritual contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jriwal
    -0.68
     fixtures
    -0.62
     subscriptions
    -0.62
     readiness
    -0.61
     chains
    -0.61
     allowances
    -0.60
     kittens
    -0.59
     pole
    -0.59
     allowance
    -0.59
     stocking
    -0.59
    POSITIVE LOGITS
    oto
    0.87
    cia
    0.76
    anche
    0.75
    ott
    0.75
    Lib
    0.75
    acher
    0.74
    ko
    0.72
    Sys
    0.72
     Tayyip
    0.72
    oka
    0.70
    Act Density 0.201%

    No Known Activations