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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of ending or concluding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſta
    -0.61
    دانشنامهٔ
    -0.59
    ſelf
    -0.57
     bonté
    -0.55
     pleaſure
    -0.54
     ſol
    -0.53
    تقاوى
    -0.53
     Monfieur
    -0.53
    PullParser
    -0.52
    ksikon
    -0.52
    POSITIVE LOGITS
    TypedDataSet
    0.54
     ajuns
    0.52
     оказались
    0.50
     landed
    0.49
     kerül
    0.49
     оказыва
    0.48
    wound
    0.47
     оказался
    0.45
     dAtA
    0.43
     wound
    0.42
    Act Density 0.150%

    No Known Activations