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

    Neuronpedia

    INDEX
    Explanations

    top ranking entities or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to high-ranking individuals or officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Frames
    -0.70
    ajor
    -0.68
     [|
    -0.67
     Interstellar
    -0.66
    TPPStreamerBot
    -0.66
     Horses
    -0.65
    irez
    -0.65
     Wilde
    -0.64
    REG
    -0.64
    ading
    -0.62
    POSITIVE LOGITS
     aide
    0.99
    most
    0.98
     scorer
    0.89
    ranking
    0.87
     aides
    0.85
     diplomat
    0.84
     drawer
    0.83
     brass
    0.82
     tier
    0.81
     earners
    0.81
    Act Density 0.045%

    No Known Activations