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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating choices, options, and conditions in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.57
    habitude
    -0.45
     hábiles
    -0.40
     juridiques
    -0.39
    httphttps
    -0.38
     geçti
    -0.38
     løpet
    -0.38
     beginnetje
    -0.37
     Ternyata
    -0.36
     selamat
    -0.36
    POSITIVE LOGITS
    сылкі
    0.64
     Мексичка
    0.61
     Infórmanos
    0.58
    Spoljašnje
    0.57
    Tikang
    0.57
    $_['
    0.53
     برانيه
    0.53
     okuyayım
    0.51
     ✭✭
    0.51
    IBar
    0.51
    Act Density 1.033%

    No Known Activations