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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate significant events or actions taken by individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ลล
    -0.16
    terior
    -0.16
    auga
    -0.15
    /DTD
    -0.15
    hoe
    -0.14
    erap
    -0.14
    477
    -0.14
    pdata
    -0.14
    ccione
    -0.13
    ousel
    -0.13
    POSITIVE LOGITS
     Guar
    0.15
     Hole
    0.15
    ron
    0.15
    aco
    0.14
    xc
    0.14
     Rounds
    0.14
    ema
    0.14
    ör
    0.14
    ily
    0.14
    oodle
    0.14
    Act Density 0.029%

    No Known Activations