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

    Neuronpedia

    INDEX
    Explanations

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

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayne
    -0.15
    ium
    -0.15
    ecimal
    -0.14
    riott
    -0.14
    atab
    -0.14
    asl
    -0.13
    oker
    -0.13
    PA
    -0.13
    Editable
    -0.13
    ão
    -0.13
    POSITIVE LOGITS
     been
    0.58
    been
    0.50
     Been
    0.46
     BEEN
    0.42
    Been
    0.39
     بÙĪدÙĩ
    0.30
     été
    0.29
     sido
    0.28
    HasBeen
    0.26
     be
    0.25
    Act Density 0.187%

    No Known Activations