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

    Neuronpedia

    INDEX
    Explanations

    scientific and research-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    statements related to scientific research and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Loyal
    -0.59
    Priv
    -0.56
    Jimmy
    -0.55
     Darrell
    -0.53
    Party
    -0.53
     Freddie
    -0.53
     veto
    -0.53
     Vanity
    -0.52
    Honest
    -0.52
    Freedom
    -0.52
    POSITIVE LOGITS
     organisms
    0.81
     hypothesized
    0.80
     biologically
    0.77
     scientists
    0.76
     biomark
    0.74
     biologists
    0.74
     researchers
    0.74
     biological
    0.73
     isot
    0.73
    ensis
    0.73
    Act Density 2.796%

    No Known Activations