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

    Neuronpedia

    INDEX
    Explanations

    words related to achievements or recognitions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of nominations for awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plan
    -0.78
    ijk
    -0.73
    fe
    -0.72
    MER
    -0.69
    GF
    -0.69
    birth
    -0.69
    Closure
    -0.68
     Spa
    -0.67
    Cost
    -0.67
    mut
    -0.67
    POSITIVE LOGITS
     nominated
    1.09
     nominate
    1.05
     nominees
    1.04
     nominating
    1.01
     nominations
    0.97
     ballots
    0.86
    daq
    0.84
     nomination
    0.82
    ividual
    0.82
    netflix
    0.81
    Act Density 0.010%

    No Known Activations