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

    Neuronpedia

    INDEX
    Explanations

    instances of state changes or transitions occurring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stället
    -0.57
    uyler
    -0.57
    feinander
    -0.55
     allmän
    -0.54
     supérieurs
    -0.54
    paign
    -0.53
     högre
    -0.53
    harapkan
    -0.53
     Awak
    -0.53
    DRO
    -0.53
    POSITIVE LOGITS
     depending
    1.01
    depending
    0.87
     Depending
    0.70
     dependiendo
    0.69
     respectively
    0.66
    Depending
    0.65
     kasarigan
    0.64
    enderror
    0.62
     autorytatywna
    0.61
    protoimpl
    0.56
    Act Density 0.398%

    No Known Activations