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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating value or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the value or merit of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thumbnails
    -0.79
    gdala
    -0.79
    pter
    -0.66
    rete
    -0.65
    yss
    -0.65
     Forge
    -0.62
    ally
    -0.62
    icken
    -0.62
    alities
    -0.62
     Vehicles
    -0.61
    POSITIVE LOGITS
     mentioning
    1.03
    iness
    0.96
     noting
    0.93
     consideration
    0.88
     remembering
    0.86
     investing
    0.83
     risking
    0.83
     checking
    0.83
     bothering
    0.81
    ily
    0.80
    Act Density 0.032%

    No Known Activations