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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that talk about endings or conclusions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BER
    -0.71
    LY
    -0.71
    ATURES
    -0.70
    ALLY
    -0.70
    aciously
    -0.69
    aris
    -0.69
    VPN
    -0.67
     firsthand
    -0.66
     accordingly
    -0.65
    PLA
    -0.64
    POSITIVE LOGITS
     country
    0.88
     smallest
    0.85
     aforementioned
    0.83
     latter
    0.77
     proverbial
    0.75
     cliff
    0.74
     equation
    0.74
     simplest
    0.74
     fray
    0.74
    spection
    0.73
    Act Density 0.248%

    No Known Activations