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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "tell" and its variations related to communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    das
    -0.17
    imal
    -0.17
    bons
    -0.17
    opc
    -0.17
    езд
    -0.17
    estr
    -0.15
    ial
    -0.15
    for
    -0.15
    bic
    -0.15
    ams
    -0.15
    POSITIVE LOGITS
     stories
    0.29
     tales
    0.29
    ingly
    0.26
    /show
    0.24
     lies
    0.24
     fortunes
    0.23
     tale
    0.23
     Stories
    0.23
     Tales
    0.22
    stories
    0.21
    Act Density 0.057%

    No Known Activations