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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize significance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ð
    -0.69
    kies
    -0.69
    Þ
    -0.65
    ouble
    -0.64
     hypers
    -0.64
    sterdam
    -0.63
    ñ
    -0.62
    anski
    -0.61
    ò
    -0.61
    Nitrome
    -0.61
    POSITIVE LOGITS
    widget
    0.72
     EVER
    0.70
    icipated
    0.67
    ":["
    0.66
    afa
    0.66
    iary
    0.65
     imaginable
    0.64
    auga
    0.64
    hesis
    0.63
     princip
    0.63
    Act Density 0.095%

    No Known Activations