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

    Neuronpedia

    INDEX
    Explanations

    words related to big size or scale

    oai_token-act-pair · gpt-3.5-turbo

    references to significant quantities or scales

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ices
    -0.80
    pai
    -0.74
    apple
    -0.73
    utenant
    -0.73
    onto
    -0.71
    Reviewed
    -0.70
    emy
    -0.70
    cling
    -0.69
    zen
    -0.68
    eve
    -0.67
    POSITIVE LOGITS
     amounts
    1.17
     quantities
    1.03
     chunks
    0.96
     scale
    0.96
     proportions
    0.95
     sums
    0.94
     disproportion
    0.87
     amount
    0.86
     swat
    0.85
     undertaking
    0.84
    Act Density 0.051%

    No Known Activations