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

    Neuronpedia

    INDEX
    Explanations

    long or complex words with specific endings or suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inth
    -0.17
    -DD
    -0.16
    ocom
    -0.16
    emi
    -0.16
     =================================================================================
    -0.15
    inson
    -0.15
    еÑı
    -0.15
    /DD
    -0.15
    untime
    -0.14
    ecome
    -0.14
    POSITIVE LOGITS
    angan
    0.18
    usu
    0.15
    adr
    0.14
    elden
    0.14
     eff
    0.14
    nos
    0.13
     Maher
    0.13
    lue
    0.13
    woods
    0.13
    dump
    0.13
    Act Density 0.010%

    No Known Activations