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

    Neuronpedia

    INDEX
    Explanations

    proper names related to politics or sports, specifically identifying individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly in the context of events or circumstances related to death or investigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aneously
    -0.75
    ishable
    -0.74
    ished
    -0.73
    ATURES
    -0.73
    ners
    -0.73
    ************
    -0.72
    atted
    -0.71
    ATURE
    -0.71
    ICAN
    -0.69
    abwe
    -0.68
    POSITIVE LOGITS
     traged
    0.93
    ortment
    0.82
    ilon
    0.74
    byss
    0.73
    xus
    0.73
     unden
    0.70
    metry
    0.70
    mos
    0.68
    sembly
    0.68
    thur
    0.68
    Act Density 0.060%

    No Known Activations