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

    Neuronpedia

    INDEX
    Explanations

    adjective-noun phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to specific groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Merit
    -0.63
     Shake
    -0.59
     Rescue
    -0.59
    iven
    -0.59
    Poké
    -0.59
     yours
    -0.58
     Adventures
    -0.58
    Lou
    -0.57
     courtesy
    -0.56
     Buster
    -0.56
    POSITIVE LOGITS
    iris
    0.85
     oppose
    0.83
     contemplate
    0.82
     perpetuate
    0.81
    rir
    0.80
    kie
    0.79
    creen
    0.78
     benefited
    0.78
     partake
    0.76
    paces
    0.75
    Act Density 0.121%

    No Known Activations