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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to engineering or mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.97
     ſtate
    -0.91
     purpoſe
    -0.89
     pleaſure
    -0.87
     ſeveral
    -0.85
     greateſt
    -0.83
     leaſt
    -0.82
     faſt
    -0.82
     Houſe
    -0.81
     ſch
    -0.79
    POSITIVE LOGITS
     استنادى
    0.71
    __':
    0.64
    Hochspringen
    0.63
    __':
    0.62
    „
    0.60
    __":
    0.60
     estekak
    0.59
     (=
    0.58
    Einzelnachweise
    0.58
    Transkript
    0.57
    Act Density 2.242%

    No Known Activations