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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or abilities

    oai_token-act-pair · gpt-3.5-turbo

    actions related to decision-making and creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.70
    alian
    -0.68
     Ridley
    -0.65
     Bung
    -0.64
     Skydragon
    -0.63
     aback
    -0.62
    luaj
    -0.61
    gypt
    -0.60
    enhagen
    -0.60
    genre
    -0.60
    POSITIVE LOGITS
     meaningful
    0.92
     judgments
    0.89
     prescriptions
    0.89
     decisions
    0.86
     orders
    0.79
     assignments
    0.78
     goods
    0.76
     messages
    0.75
     money
    0.74
     medicines
    0.74
    Act Density 0.405%

    No Known Activations