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

    Neuronpedia

    INDEX
    Explanations

    words related to legal terminology and defense

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

    "Def" at the beginning of a line

    np_acts-logits-general · gemini-2.0-flash

    words starting with Def

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.94
     lenker
    -0.85
    DockStyle
    -0.79
     препратки
    -0.79
     mergeFrom
    -0.79
     يتيمه
    -0.78
    ^(@)
    -0.78
    IonicModule
    -0.76
    Rujuakan
    -0.73
    Autoritní
    -0.72
    POSITIVE LOGITS
     Def
    0.74
     DEF
    0.71
    Def
    0.71
    DEF
    0.68
     against
    0.57
     def
    0.56
    def
    0.56
     undef
    0.49
     quoi
    0.49
     déf
    0.49
    Act Density 0.122%

    No Known Activations