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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -1.14
     '\\;'
    -0.96
    хьтан
    -0.89
     Efq
    -0.89
    HideFlags
    -0.87
    neurial
    -0.84
     cdti
    -0.82
     Jefus
    -0.81
     doubtnut
    -0.80
    pushFollow
    -0.78
    POSITIVE LOGITS
    \
    0.95
    </em>
    0.84
     \
    0.72
      
    0.70
    [toxicity=0]
    0.70
    </tr>
    0.69
    <strong>
    0.69
    </u>
    0.68
    <tr>
    0.66
    </i>
    0.66
    Act Density 0.014%

    No Known Activations