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

    Neuronpedia

    INDEX
    Explanations

    various states and transformations of "things"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grade
    -0.40
     transfieras
    -0.40
     autorytatywna
    -0.39
     permanently
    -0.39
    bino
    -0.38
     Beacons
    -0.38
     purpose
    -0.38
     Sabha
    -0.38
    fällig
    -0.37
    atase
    -0.37
    POSITIVE LOGITS
     things
    0.76
    Things
    0.73
    things
    0.70
     ब्रेकडाउन
    0.67
     Things
    0.67
     THINGS
    0.67
     initComponents
    0.66
    THINGS
    0.65
    everything
    0.61
     situazione
    0.57
    Act Density 0.331%

    No Known Activations