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

    Neuronpedia

    INDEX
    Explanations

    economic and policy-related terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to economic and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ety
    -0.78
    £ı
    -0.70
    eus
    -0.66
    scription
    -0.65
    lord
    -0.62
    REDACTED
    -0.62
    ocl
    -0.61
    iger
    -0.60
    igm
    -0.60
    yon
    -0.60
    POSITIVE LOGITS
     albeit
    0.98
     improve
    0.93
     including
    0.93
     thereby
    0.90
    particularly
    0.88
    including
    0.84
    especially
    0.84
     Improve
    0.83
     includ
    0.83
     improves
    0.82
    Act Density 0.377%

    No Known Activations