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

    Neuronpedia

    INDEX
    Explanations

    terms related to laws, regulations, and technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to current laws and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     extraord
    -0.65
     Sat
    -0.59
     Brit
    -0.58
    urat
    -0.58
     Pri
    -0.58
     holiest
    -0.57
    sung
    -0.56
    DERR
    -0.56
     coveted
    -0.56
    liga
    -0.55
    POSITIVE LOGITS
    ologies
    0.81
    frames
    0.74
     iteration
    0.74
     incarnation
    0.73
    bernatorial
    0.73
     trajectory
    0.73
     administrations
    0.68
     iterations
    0.67
     parad
    0.66
     paradigm
    0.65
    Act Density 0.413%

    No Known Activations