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

    Neuronpedia

    INDEX
    Explanations

    specific nouns, such as proper nouns, objects, and body parts

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to specific objects, actions, and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    with
    -0.79
     withd
    -0.75
    With
    -0.61
    onds
    -0.61
    ividual
    -0.60
    estate
    -0.59
    infeld
    -0.58
    owship
    -0.57
     With
    -0.57
    eworld
    -0.57
    POSITIVE LOGITS
     intact
    1.05
     attached
    0.99
     enabled
    0.93
     thrown
    0.90
     looming
    0.89
     strapped
    0.89
     impunity
    0.83
     flourish
    0.82
     draped
    0.82
     inserted
    0.80
    Act Density 0.517%

    No Known Activations