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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional situations or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.05
    ]();
    -0.87
    пенно
    -0.84
    はじめに
    -0.78
    nambuco
    -0.73
     לכם
    -0.73
     لیے
    -0.71
     להם
    -0.69
     mergeFrom
    -0.68
     التالية
    -0.67
    POSITIVE LOGITS
     sepen
    0.79
    儘
    0.78
     kív
    0.77
     LIRE
    0.76
     ugy
    0.75
    VIOUS
    0.74
     defaultstate
    0.74
     näm
    0.72
     întâ
    0.72
    Бли
    0.71
    Act Density 0.566%

    No Known Activations