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

    Neuronpedia

    INDEX
    Explanations

    questions or phrases related to queries

    oai_token-act-pair · gpt-3.5-turbo

    question phrases that begin with "What."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    charg
    -0.69
    onz
    -0.68
    psc
    -0.68
    ento
    -0.61
    eering
    -0.60
    ãģĨ
    -0.58
    iege
    -0.58
    ivery
    -0.57
    istani
    -0.57
    interstitial
    -0.56
    POSITIVE LOGITS
     distinguishes
    1.20
     happens
    1.14
     bothers
    1.13
    soever
    1.13
     emerges
    1.09
     separates
    1.06
     constitutes
    1.06
     distur
    1.01
     happened
    0.99
     mattered
    0.98
    Act Density 0.063%

    No Known Activations