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

    Neuronpedia

    INDEX
    Explanations

    names of famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to notable directors, films, and cultural icons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shown
    -0.72
    leased
    -0.70
    large
    -0.70
    profits
    -0.69
    events
    -0.66
    olars
    -0.65
     LIMITED
    -0.65
    ESCO
    -0.64
    aughters
    -0.64
    anwhile
    -0.64
    POSITIVE LOGITS
    esque
    1.56
     mentality
    1.15
     vibe
    1.14
     style
    1.07
    ian
    1.06
     kind
    1.02
     Syndrome
    0.98
     type
    0.96
     bullshit
    0.96
     proportions
    0.96
    Act Density 0.381%

    No Known Activations