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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to individual people or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kitchen
    -0.85
     Seat
    -0.70
     Verb
    -0.69
     Downs
    -0.68
     Norton
    -0.68
     Deadly
    -0.65
     Little
    -0.64
     Dame
    -0.64
    UP
    -0.64
    forth
    -0.64
    POSITIVE LOGITS
    ividual
    1.22
    individual
    1.13
     individuals
    1.08
    ortium
    0.99
     identifiable
    0.93
     Individuals
    0.89
     enthusi
    0.88
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    0.85
    isms
    0.84
     volunte
    0.82
    Act Density 0.010%

    No Known Activations