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

    Neuronpedia

    INDEX
    Explanations

    requests for advice and direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Doing
    -0.97
     Doing
    -0.94
     DOING
    -0.90
    doing
    -0.78
    Done
    -0.77
     Done
    -0.74
     ſt
    -0.70
     DONE
    -0.69
     ſta
    -0.64
     ſte
    -0.61
    POSITIVE LOGITS
     do
    1.25
     does
    0.69
     did
    0.43
     vastaan
    0.42
    do
    0.41
     du
    0.41
     saira
    0.40
     da
    0.39
     dne
    0.39
     due
    0.39
    Act Density 0.212%

    No Known Activations