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

    Neuronpedia

    INDEX
    Explanations

    references to historical events and significant locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     delt
    -0.17
    λÏĮγ
    -0.16
    ente
    -0.15
    OMET
    -0.15
    ENTE
    -0.15
    ENU
    -0.14
     Tent
    -0.14
    Fx
    -0.14
    æľºåľº
    -0.14
    enu
    -0.14
    POSITIVE LOGITS
     Titanic
    0.31
    Titan
    0.19
     steer
    0.19
     RMS
    0.17
     iceberg
    0.17
     passenger
    0.17
    char
    0.17
    ney
    0.16
     passengers
    0.16
     Passenger
    0.16
    Act Density 0.007%

    No Known Activations