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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical space missions and ingredients for cooking or baking

    oai_token-act-pair · gpt-3.5-turbo

    references to the Apollo program and mentions of vanilla

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wich
    -0.95
    later
    -0.84
    ering
    -0.83
    ship
    -0.79
    ividual
    -0.76
    lings
    -0.75
    igan
    -0.73
    rences
    -0.73
    ishes
    -0.73
    ishers
    -0.72
    POSITIVE LOGITS
    chio
    0.87
    urity
    0.78
    ollo
    0.74
    uracy
    0.72
    ãĥ¼ãĥĨãĤ£
    0.70
    urnal
    0.69
     Creed
    0.66
    ctic
    0.66
     Grounds
    0.66
    BILITIES
    0.66
    Act Density 0.084%

    No Known Activations