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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future actions, commitments, or capabilities

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

    introducing or explaining actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.91
    webElementXpaths
    -0.91
    GEBURTSDATUM
    -0.81
     témoig
    -0.80
     zwiſchen
    -0.80
    ロウィン
    -0.78
    ſammen
    -0.77
    rungsseite
    -0.76
     ddelwed
    -0.75
     $_(
    -0.73
    POSITIVE LOGITS
     saja
    0.28
     sevi
    0.28
    Our
    0.25
     Dabei
    0.24
    from
    0.24
    zige
    0.24
     Our
    0.24
     twor
    0.23
     [
    0.23
    liggende
    0.23
    Act Density 0.017%

    No Known Activations