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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe methods or approaches in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.72
     againſt
    -0.69
     tranf
    -0.65
     houſe
    -0.65
     Audiodateien
    -0.64
     objectAtIndex
    -0.63
     Nimbus
    -0.63
     histories
    -0.63
     EconPapers
    -0.62
     Hift
    -0.62
    POSITIVE LOGITS
     manner
    0.88
     way
    0.88
     manière
    0.78
     ways
    0.75
     maniera
    0.72
     fashion
    0.70
     manera
    0.69
     Weise
    0.64
     образом
    0.63
     maneras
    0.62
    Act Density 0.266%

    No Known Activations