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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "have" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obre
    -0.15
     olsun
    -0.14
    .jp
    -0.14
    anca
    -0.14
    ollen
    -0.14
    481
    -0.14
     ÑģÑħод
    -0.14
    lung
    -0.14
    nut
    -0.13
    rab
    -0.13
    POSITIVE LOGITS
     no
    0.23
     yet
    0.22
     heard
    0.21
     always
    0.20
     never
    0.20
    yet
    0.19
     seen
    0.19
     hear
    0.18
     often
    0.18
     to
    0.17
    Act Density 0.177%

    No Known Activations