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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "to do" or expressions of obligation and responsibility

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

    し and negation, reason, or consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ualla
    -0.47
    acabana
    -0.42
    ActionMode
    -0.42
     VOY
    -0.39
    {(-
    -0.38
     jura
    -0.38
     Mera
    -0.38
    OneToMany
    -0.38
     =~
    -0.38
     =>
    -0.37
    POSITIVE LOGITS
    し
    1.91
     し
    1.10
    をし
    0.98
    にし
    0.80
    しの
    0.79
    がし
    0.79
    しと
    0.77
    しが
    0.75
    しな
    0.73
    しも
    0.69
    Act Density 0.002%

    No Known Activations