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

    Neuronpedia

    INDEX
    Explanations

    phrases related to measurements of weight or quantity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mass and physical properties in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullivan
    -0.75
    ctuary
    -0.74
    itled
    -0.72
    itual
    -0.69
    uj
    -0.68
    soDeliveryDate
    -0.68
    JECT
    -0.68
    employment
    -0.68
    ovie
    -0.68
    agall
    -0.68
    POSITIVE LOGITS
     ratio
    0.91
     difference
    0.88
     computed
    0.88
     ranges
    0.87
     squared
    0.83
     ratios
    0.81
     discrepancy
    0.79
     coefficient
    0.78
     multiplier
    0.78
     threshold
    0.78
    Act Density 0.258%

    No Known Activations