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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -1.16
     Jefus
    -1.13
     pleaſure
    -1.13
     Monfieur
    -1.03
     poffe
    -0.99
    ſelf
    -0.99
     Majefty
    -0.98
     uſ
    -0.98
     faſt
    -0.98
     houſe
    -0.96
    POSITIVE LOGITS
     taget
    0.53
     ar
    0.50
     use
    0.50
    </i>
    0.49
     put
    0.48
    ,
    0.47
    localVar
    0.46
    <i>
    0.46
    </b>
    0.45
     go
    0.45
    Act Density 0.022%

    No Known Activations