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

    Neuronpedia

    INDEX
    Explanations

    words related to nuclear power plants or technical terms within various fields

    oai_token-act-pair · gpt-3.5-turbo

    terms related to nuclear energy and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     channels
    -0.66
     pillars
    -0.65
     avenues
    -0.64
     bins
    -0.64
     fixtures
    -0.64
     priorities
    -0.64
     divisions
    -0.62
    ooks
    -0.62
     departments
    -0.62
    headers
    -0.62
    POSITIVE LOGITS
    robe
    0.84
     or
    0.81
    ifier
    0.80
    chuk
    0.80
    ogram
    0.78
    .–
    0.77
    ographer
    0.76
     anywhere
    0.75
    uble
    0.75
     someday
    0.73
    Act Density 0.453%

    No Known Activations