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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "have" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     perſon
    -1.00
     beſt
    -0.97
     houſe
    -0.95
     myſelf
    -0.92
     reaſon
    -0.90
     Jefus
    -0.89
     pleaſure
    -0.89
    ſelf
    -0.89
     ſtate
    -0.88
     purpoſe
    -0.88
    POSITIVE LOGITS
     a
    0.78
    AreEqual
    0.78
     an
    0.76
     the
    0.68
     with
    0.68
    boxylic
    0.68
    flashdata
    0.67
     }^{(
    0.67
    Tiene
    0.65
    addAttribute
    0.63
    Act Density 0.086%

    No Known Activations