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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making or planning

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to courses of action or paths towards various outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orporated
    -0.78
    pload
    -0.76
    ores
    -0.74
    uania
    -0.73
    nice
    -0.71
    cup
    -0.71
    chens
    -0.70
    ldom
    -0.69
    leeve
    -0.66
    mson
    -0.65
    POSITIVE LOGITS
     progression
    0.92
     development
    0.90
     advancement
    0.87
     trajectory
    0.83
     events
    0.82
     traject
    0.81
     unfold
    0.81
     pathways
    0.80
     causation
    0.79
     descent
    0.79
    Act Density 0.227%

    No Known Activations