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

    Neuronpedia

    INDEX
    Explanations

    contractions indicating possession or obligation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "have" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lapt
    -0.65
     Sparrow
    -0.65
    é¾įå¥ij士
    -0.64
    matically
    -0.62
    Subject
    -0.59
    Layout
    -0.59
     GOODMAN
    -0.57
    ological
    -0.57
    ologically
    -0.56
    Rated
    -0.56
    POSITIVE LOGITS
    ctors
    0.95
    mber
    0.91
    tt
    0.90
    ggie
    0.90
    theless
    0.87
    tti
    0.86
     Been
    0.83
     been
    0.83
    ggies
    0.83
    tta
    0.82
    Act Density 0.029%

    No Known Activations