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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating statements or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cruiser
    -0.79
    allery
    -0.68
    artment
    -0.66
    artments
    -0.66
     Globe
    -0.62
    oston
    -0.60
    ibal
    -0.58
    onut
    -0.58
    swick
    -0.58
     fingert
    -0.58
    POSITIVE LOGITS
     aloud
    1.19
     goodbye
    1.11
     loudly
    1.11
     louder
    0.98
     Goodbye
    0.88
     bluff
    0.81
     loud
    0.74
     farewell
    0.70
    ript
    0.68
    displayText
    0.68
    Act Density 0.343%

    No Known Activations