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

    Neuronpedia

    INDEX
    Explanations

    phrases or words enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotations and phrases enclosed in quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Arn
    -0.73
     Alv
    -0.73
     wrinkles
    -0.71
     Asians
    -0.70
     Izan
    -0.70
     Elements
    -0.69
     shores
    -0.69
     Ern
    -0.69
     Debor
    -0.68
    culosis
    -0.68
    POSITIVE LOGITS
    complete
    1.16
    classic
    1.13
    significant
    1.10
    very
    1.08
    highly
    1.07
    little
    1.07
    false
    1.06
    political
    1.06
    reasonable
    1.05
    cheat
    1.05
    Act Density 0.026%

    No Known Activations