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

    Neuronpedia

    INDEX
    Explanations

    references to opposing perspectives or parties in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oprecip
    -0.70
    SqlDataReader
    -0.68
    principalColumn
    -0.67
    PropertyChanging
    -0.61
    __*/
    -0.58
    rrggbb
    -0.58
    ]))
    -0.57
    HasKey
    -0.56
     насељу
    -0.53
    hartt
    -0.52
    POSITIVE LOGITS
     sides
    1.64
     Sides
    1.52
    Sides
    1.47
    sides
    1.35
     ends
    0.82
     exceed
    0.76
     lados
    0.76
     Ends
    0.76
     parties
    0.75
     Parties
    0.73
    Act Density 0.122%

    No Known Activations