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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric or special character sequences that follow a consistent pattern or format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    βα
    -0.17
    /Dk
    -0.15
    /rfc
    -0.15
    عÙĬ
    -0.15
    flix
    -0.14
    ollow
    -0.14
    ستاÙĨ
    -0.14
    Ìī
    -0.14
    nowledge
    -0.14
    IIIK
    -0.14
    POSITIVE LOGITS
    Locker
    0.15
    locker
    0.14
     ps
    0.14
     secret
    0.14
     x
    0.14
    activ
    0.13
     y
    0.13
     t
    0.13
     proper
    0.13
    wb
    0.13
    Act Density 0.081%

    No Known Activations