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

    Neuronpedia

    INDEX
    Explanations

    specific decisions or actions being taken regarding various subjects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "decision."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vae
    -0.78
    english
    -0.72
    eco
    -0.71
    ingers
    -0.69
    sung
    -0.69
    ubric
    -0.68
    amen
    -0.67
    icas
    -0.66
    nat
    -0.66
    ogene
    -0.65
    POSITIVE LOGITS
     makers
    0.99
     ACTIONS
    0.86
     maker
    0.85
     decisions
    0.82
     decision
    0.79
    jar
    0.79
     Garc
    0.73
     regarding
    0.72
    maker
    0.70
    crop
    0.70
    Act Density 0.035%

    No Known Activations