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

    Neuronpedia

    INDEX
    Explanations

    Latin words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to electronic components and scientific processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     KH
    -0.83
     Winnipeg
    -0.77
     JACK
    -0.76
    DK
    -0.73
     Nightmares
    -0.73
     Beckham
    -0.72
    boarding
    -0.70
     Hockey
    -0.69
    OVER
    -0.69
     Saudis
    -0.69
    POSITIVE LOGITS
    ibus
    1.32
    orem
    1.21
    orum
    1.21
    iae
    1.17
     nomine
    1.16
    È
    1.14
     qui
    1.10
     exerc
    1.09
     exting
    1.07
     Deus
    1.05
    Act Density 0.161%

    No Known Activations