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

    Neuronpedia

    INDEX
    Explanations

    phrases related to errors or issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Something"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     avail
    -0.67
     counters
    -0.64
     maximizing
    -0.62
     remaining
    -0.62
     territorial
    -0.61
     limited
    -0.60
     expected
    -0.58
     deductions
    -0.58
     cross
    -0.58
     hyd
    -0.58
    POSITIVE LOGITS
     Something
    3.15
    Something
    2.53
    something
    2.10
     Someone
    1.92
     Somebody
    1.84
     Somewhere
    1.72
    Someone
    1.68
     Things
    1.54
     Somehow
    1.44
     Anything
    1.39
    Act Density 0.015%

    No Known Activations