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

    Neuronpedia

    INDEX
    Explanations

    the word "z" at the end of certain entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'z'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scots
    -0.71
     ransom
    -0.71
     Southeast
    -0.66
     entail
    -0.63
     behavi
    -0.63
     foss
    -0.60
     Malays
    -0.56
     butt
    -0.56
     Secret
    -0.56
     Cheong
    -0.56
    POSITIVE LOGITS
    ombie
    1.40
    ewski
    1.21
    enegger
    1.21
    ombies
    1.16
    alez
    1.10
    ealous
    1.07
    ymes
    1.06
    ebra
    1.05
    gerald
    1.03
    arella
    1.00
    Act Density 0.064%

    No Known Activations