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

    Neuronpedia

    INDEX
    Explanations

    words related to conflict and struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Manhattan
    -0.66
    isode
    -0.66
     cottage
    -0.64
     sled
    -0.63
     board
    -0.63
     decomp
    -0.61
     chronological
    -0.60
     Somerset
    -0.60
     assemb
    -0.59
     charm
    -0.59
    POSITIVE LOGITS
    ¬
    1.14
    ¡
    1.11
    ¤
    1.07
    Ĵ
    1.04
    ı
    1.00
    ľ
    0.99
    ¼
    0.97
    ĸ
    0.96
    _.
    0.94
    Ļ
    0.94
    Act Density 0.248%

    No Known Activations