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

    Neuronpedia

    INDEX
    Explanations

    expressions of commitments or promises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    future actions promised or stated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.48
    -0.38
    солю
    -0.38
    Diret
    -0.36
    Sabes
    -0.35
     solides
    -0.35
     Gå
    -0.34
     Чита
    -0.33
     Erster
    -0.33
    sworth
    -0.33
    POSITIVE LOGITS
    0.57
    BufferException
    0.56
     promised
    0.54
    transQ
    0.51
     RemoteException
    0.51
    expandindo
    0.51
     autorytatywna
    0.50
    PerformLayout
    0.49
    ніципалі
    0.47
    ">//
    0.47
    Act Density 0.055%

    No Known Activations