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

    Neuronpedia

    INDEX
    Explanations

    words related to legislation and policy-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to environmental and economic impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '.
    -0.80
    .).
    -0.79
    ''.
    -0.76
    .'
    -0.73
    ?).
    -0.71
    .]
    -0.66
     attRot
    -0.65
    ".
    -0.65
    }.
    -0.64
    '."
    -0.64
    POSITIVE LOGITS
     outpatient
    0.62
    -,
    0.55
     geographically
    0.55
     âĪ¼
    0.54
     physically
    0.54
     physical
    0.54
     nighttime
    0.51
    physical
    0.51
     foundational
    0.51
     nonviolent
    0.51
    Act Density 1.793%

    No Known Activations