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

    Neuronpedia

    INDEX
    Explanations

    the verb "is" at varying levels of intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "is."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stood
    -0.72
    rouse
    -0.65
     Chero
    -0.64
     ÂŃ
    -0.62
    */
    -0.60
    enges
    -0.58
     Isles
    -0.57
    esides
    -0.57
    âĶ
    -0.56
    edIn
    -0.55
    POSITIVE LOGITS
    ometric
    1.05
    senal
    1.00
    omorphic
    0.96
    rael
    0.96
    cussion
    0.91
    Offline
    0.90
     deprecated
    0.90
     hereby
    0.90
    othermal
    0.85
    omorph
    0.84
    Act Density 0.059%

    No Known Activations