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

    Neuronpedia

    INDEX
    Explanations

    phrases related to methods of communication and connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nt
    -0.16
    usercontent
    -0.16
    woke
    -0.15
    ma
    -0.15
    GetProperty
    -0.15
    ning
    -0.14
    wick
    -0.14
    ctr
    -0.14
    eres
    -0.14
    ale
    -0.14
    POSITIVE LOGITS
     means
    0.18
    ought
    0.18
    ë¡ľëĬĶ
    0.17
     versa
    0.17
    857
    0.16
    umbnail
    0.16
    /in
    0.16
    761
    0.16
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.15
    664
    0.15
    Act Density 0.017%

    No Known Activations