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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing strong emotions or opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize assertion or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cruiser
    -0.74
    ibal
    -0.62
    swick
    -0.61
     fingert
    -0.58
     Lauder
    -0.58
    artment
    -0.56
     Mechan
    -0.56
    allery
    -0.56
     Liver
    -0.55
    ensing
    -0.54
    POSITIVE LOGITS
     goodbye
    1.08
     aloud
    1.02
     loudly
    0.93
     farewell
    0.84
     bluff
    0.82
     Goodbye
    0.76
     louder
    0.75
     hello
    0.74
    ript
    0.72
     loud
    0.72
    Act Density 0.263%

    No Known Activations