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

    Neuronpedia

    INDEX
    Explanations

    terms related to explosives and weaponry

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

    words and objects related to weapons, explosives, and dangerous sharp items.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     Ringo
    -0.40
    Rptr
    -0.39
    geben
    -0.38
    fört
    -0.37
     Murdoch
    -0.36
     commerciale
    -0.36
    xmlWriter
    -0.36
    fras
    -0.36
     виправивши
    -0.35
     beschränkt
    -0.35
    POSITIVE LOGITS
     trap
    0.66
    TypedDataSet
    0.59
     mines
    0.57
     traps
    0.56
     mine
    0.54
    Trap
    0.54
    trap
    0.52
    Mines
    0.52
    mybatisplus
    0.52
     MINES
    0.51
    Act Density 0.163%

    No Known Activations