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

    Neuronpedia

    INDEX
    Explanations

    terms related to processes and measurements in a technical or scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     εικό
    -0.57
    Спољашње
    -0.56
     ſever
    -0.56
     habet
    -0.54
    AnchorStyles
    -0.53
     thiệu
    -0.53
    StoryboardSegue
    -0.52
     pleaſure
    -0.51
     houſe
    -0.51
     tranſ
    -0.50
    POSITIVE LOGITS
     x
    0.94
     $
    0.92
     p
    0.92
     $\
    0.89
     q
    0.88
     h
    0.87
     r
    0.86
     X
    0.85
     λ
    0.85
     n
    0.84
    Act Density 4.806%

    No Known Activations