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

    Neuronpedia

    INDEX
    Explanations

    words related to seeking help or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dla
    -0.70
     ſta
    -0.66
     BrowserModule
    -0.64
     eſſ
    -0.62
     dieß
    -0.61
     purpoſe
    -0.61
    ſelf
    -0.61
     viſ
    -0.60
     geſ
    -0.59
     için
    -0.59
    POSITIVE LOGITS
     fo
    0.82
     fot
    0.78
     foe
    0.77
     tor
    0.77
     fro
    0.73
     fort
    0.71
     fore
    0.68
     fer
    0.68
     fir
    0.67
     fr
    0.64
    Act Density 0.242%

    No Known Activations