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

    Neuronpedia

    INDEX
    Explanations

    words related to weight and measurement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to weight measurements and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.60
    bid
    -0.58
    itus
    -0.55
    href
    -0.55
    ossom
    -0.55
    ertain
    -0.54
    Bridge
    -0.54
    adies
    -0.53
    ffe
    -0.53
    acca
    -0.53
    POSITIVE LOGITS
     approximately
    1.00
     660
    0.91
     approx
    0.91
     440
    0.88
     Approximately
    0.86
     840
    0.86
     550
    0.84
     340
    0.84
     275
    0.83
     335
    0.83
    Act Density 0.070%

    No Known Activations