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

    Neuronpedia

    INDEX
    Explanations

    words related to film sets

    oai_token-act-pair · gpt-3.5-turbo

    references to film production settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.88
    vernment
    -0.72
    ibly
    -0.69
    aud
    -0.65
    ished
    -0.64
    ishable
    -0.64
    ishy
    -0.62
    maxwell
    -0.62
    ãĤĭ
    -0.62
     saline
    -0.62
    POSITIVE LOGITS
    list
    0.96
    tle
    0.93
    offs
    0.91
    opsis
    0.89
    rac
    0.88
    ters
    0.87
    lists
    0.86
    mate
    0.83
    ropolis
    0.78
    ter
    0.76
    Act Density 0.036%

    No Known Activations