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

    Neuronpedia

    INDEX
    Explanations

    combinations or compounds of words

    oai_token-act-pair · gpt-3.5-turbo

    terms related to combination or merging of elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Passage
    -0.70
     Confederacy
    -0.70
     Wilde
    -0.67
     dear
    -0.67
    ħĭ
    -0.65
     Payton
    -0.65
     hospitality
    -0.63
     debtor
    -0.62
    writers
    -0.62
     Myster
    -0.62
    POSITIVE LOGITS
    inations
    1.29
    inators
    1.17
    ination
    1.11
    ined
    1.03
    inatory
    1.03
    inated
    1.00
    inator
    0.98
    inational
    0.94
    icit
    0.91
    ocation
    0.91
    Act Density 0.016%

    No Known Activations