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

    Neuronpedia

    INDEX
    Explanations

    words that express causation or result-oriented phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.71
     impea
    -0.59
    ContentLoaded
    -0.59
    vény
    -0.58
    rzost
    -0.58
    antMatchers
    -0.58
    ératures
    -0.58
    lores
    -0.57
    oltà
    -0.57
    ület
    -0.57
    POSITIVE LOGITS
    Так
    0.98
     Así
    0.97
     Так
    0.96
     así
    0.94
    Así
    0.91
     so
    0.89
     так
    0.88
     näin
    0.86
     assim
    0.86
     så
    0.82
    Act Density 0.110%

    No Known Activations