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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates or periods of time

    oai_token-act-pair · gpt-3.5-turbo

    historical references and significant time-related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.66
    Vice
    -0.61
    ãĥ¼ãĥ³
    -0.56
    ãĥĦ
    -0.54
    enegger
    -0.54
    Nonetheless
    -0.53
     itself
    -0.52
    Runner
    -0.51
    \\\\\\\\
    -0.50
    Attempt
    -0.50
    POSITIVE LOGITS
     converge
    0.74
     collide
    0.73
     vary
    0.70
     differ
    0.69
     abound
    0.64
     varying
    0.63
     aren
    0.62
     backgrounds
    0.61
     are
    0.60
     prolifer
    0.60
    Act Density 1.249%

    No Known Activations