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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "have" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.13
     itſelf
    -1.11
     perſon
    -1.03
     Jefus
    -1.00
     Cæsar
    -1.00
     مشين
    -0.98
     houſe
    -0.98
     themſelves
    -0.96
     Monfieur
    -0.95
     ſtate
    -0.94
    POSITIVE LOGITS
     a
    0.74
     an
    0.74
     tiene
    0.66
     Had
    0.63
     With
    0.60
    Tiene
    0.60
     with
    0.60
     tienes
    0.59
     tenga
    0.58
     or
    0.57
    Act Density 0.082%

    No Known Activations