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

    Neuronpedia

    INDEX
    Explanations

    positive evaluations or acknowledgments

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating positive evaluations of performance or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     petitions
    -0.71
     forms
    -0.70
    artifacts
    -0.69
     fronts
    -0.69
     markers
    -0.69
     constructs
    -0.68
     outlawed
    -0.68
    limits
    -0.66
    apps
    -0.65
     Trees
    -0.65
    POSITIVE LOGITS
     chunk
    1.25
     deal
    1.22
     amount
    1.02
     approximation
    0.97
     dose
    0.96
    enough
    0.96
     job
    0.95
     sized
    0.92
     impression
    0.92
     idea
    0.90
    Act Density 0.082%

    No Known Activations