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

    Neuronpedia

    INDEX
    Explanations

    phrases related to completing tasks or roles

    oai_token-act-pair · gpt-3.5-turbo

    references to completing or occupying spaces or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verbal
    -0.66
    peer
    -0.65
    conduct
    -0.65
    aji
    -0.63
    wcs
    -0.62
    dar
    -0.62
    behavior
    -0.61
    appro
    -0.60
    rf
    -0.60
    Friends
    -0.60
    POSITIVE LOGITS
     vacancies
    0.94
     gaps
    0.89
     coffers
    0.81
     fills
    0.80
    fill
    0.78
     fill
    0.78
     notebooks
    0.74
     torches
    0.74
     shortages
    0.74
     prescriptions
    0.74
    Act Density 0.026%

    No Known Activations