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

    Neuronpedia

    INDEX
    Explanations

    legal and procedural phrases related to duties, rights, and obligations

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

    shall and shall not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     󰀄
    -0.41
     worried
    -0.37
     pinulongan
    -0.36
    Dónde
    -0.35
     zaten
    -0.35
     vanskelig
    -0.35
     Cárdenas
    -0.34
     fantasmas
    -0.34
     ľ
    -0.34
     fantasma
    -0.34
    POSITIVE LOGITS
     shall
    0.68
     Shall
    0.66
    shall
    0.62
    SBATCH
    0.59
    Shall
    0.56
    saraba
    0.56
    AnchorStyles
    0.55
     TestBed
    0.54
    SequentialGroup
    0.54
    /**
    0.53
    Act Density 0.019%

    No Known Activations