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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating willingness to take action or sacrifice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.74
     autorytatywna
    -0.74
     насељу
    -0.73
    SharedDtor
    -0.72
    IBOutlet
    -0.71
    Vidite
    -0.67
    出版年
    -0.66
     '\\;'
    -0.65
    ]")]
    -0.63
    styleable
    -0.62
    POSITIVE LOGITS
     sacrifice
    1.28
     sacrifices
    1.18
     sacrificing
    1.15
     sacrificed
    1.06
     sacrific
    1.04
     Sacrifice
    1.04
    sacrifice
    1.00
     Sacrific
    1.00
    sacrific
    0.98
     sacri
    0.84
    Act Density 0.214%

    No Known Activations