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

    Neuronpedia

    INDEX
    Explanations

    technical specifications such as model numbers and configurations

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or codes typically related to technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    querque
    -0.78
    ogene
    -0.71
    enegger
    -0.68
     unemployed
    -0.66
     bere
    -0.65
     multiplying
    -0.63
     stroke
    -0.62
     snowball
    -0.62
    oooooooooooooooo
    -0.61
     swipe
    -0.61
    POSITIVE LOGITS
    DM
    1.11
    VB
    0.99
    DX
    0.98
    XX
    0.98
    CB
    0.96
    NAT
    0.93
    014
    0.93
    MH
    0.93
    RD
    0.92
    DW
    0.91
    Act Density 0.084%

    No Known Activations