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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ska
    -0.14
    оÑĢд
    -0.14
    inke
    -0.13
     Recon
    -0.13
    structions
    -0.13
     SEEK
    -0.13
    apr
    -0.13
     Legends
    -0.13
    orca
    -0.13
    amber
    -0.13
    POSITIVE LOGITS
    ovich
    0.18
    lopen
    0.17
    atar
    0.17
    arie
    0.16
    ATAR
    0.14
    itches
    0.14
    etooth
    0.14
    eph
    0.14
    arya
    0.14
    dej
    0.14
    Act Density 0.147%

    No Known Activations