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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or leaders, particularly within a geopolitical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Palest
    -0.82
    Rust
    -0.76
     goat
    -0.71
    Pod
    -0.69
    士
    -0.67
     Boyle
    -0.66
     Kafka
    -0.65
    ãĥĥ
    -0.64
     Cycling
    -0.62
    CAST
    -0.62
    POSITIVE LOGITS
    ui
    1.08
    ook
    0.95
    sung
    0.94
    oo
    0.94
    oon
    0.93
    won
    0.90
    ua
    0.88
    ae
    0.86
    wei
    0.85
    uan
    0.84
    Act Density 0.061%

    No Known Activations