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

    Neuronpedia

    INDEX
    Explanations

    words related to disenfranchisement and empowerment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disenfranchisement and marginalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lings
    -0.92
    forth
    -0.82
    lights
    -0.72
    geist
    -0.71
    glers
    -0.69
    MAN
    -0.68
    rers
    -0.68
    land
    -0.67
     lag
    -0.67
    WER
    -0.67
    POSITIVE LOGITS
    ises
    1.25
    ising
    1.19
    ise
    1.13
    isers
    1.10
    pload
    1.04
    ised
    1.04
    isable
    1.01
    etheus
    0.99
    otic
    0.98
    iser
    0.97
    Act Density 0.038%

    No Known Activations