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

    Neuronpedia

    INDEX
    Explanations

    phrases addressing or introducing a specific topic or concept

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce or emphasize a point or argument

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Archdemon
    -0.80
    omas
    -0.69
    oons
    -0.65
    tery
    -0.65
    ettings
    -0.64
    dan
    -0.64
    Leaks
    -0.64
    asons
    -0.64
     dime
    -0.63
     ({
    -0.63
    POSITIVE LOGITS
     caveats
    0.88
     caveat
    0.83
     disclaimer
    0.80
     backdrop
    0.74
     knowledge
    0.74
     realization
    0.72
     terminology
    0.68
     reasoning
    0.68
     consideration
    0.65
     information
    0.65
    Act Density 0.099%

    No Known Activations