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

    Neuronpedia

    INDEX
    Explanations

    words related to stopping or ceasing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     médicaux
    -0.95
     noires
    -0.87
     deportivos
    -0.85
     fermés
    -0.84
     secco
    -0.78
     colorés
    -0.72
    UnusedPrivate
    -0.72
     vertes
    -0.69
    DockStyle
    -0.69
     recommandons
    -0.68
    POSITIVE LOGITS
    Starting
    0.61
     Starting
    0.60
     starting
    0.57
    )");
    0.54
    starting
    0.52
    ]));
    0.51
    Encoding
    0.51
     resumed
    0.50
    setVerticalGroup
    0.50
    uguetes
    0.49
    Act Density 0.105%

    No Known Activations