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

    Neuronpedia

    INDEX
    Explanations

    phrases related to creating or setting things up

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "create" followed by various nouns indicating projects or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mong
    -0.69
    lings
    -0.67
    seekers
    -0.67
    erers
    -0.65
    aunts
    -0.65
     Sle
    -0.63
    enance
    -0.63
    treated
    -0.62
    gnu
    -0.61
    writers
    -0.61
    POSITIVE LOGITS
     havoc
    0.80
     distinct
    0.73
     distinctive
    0.71
     footprint
    0.70
     unique
    0.70
     rift
    0.69
     viable
    0.68
    aganda
    0.68
     caliphate
    0.67
    ctica
    0.67
    Act Density 0.314%

    No Known Activations