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

    Neuronpedia

    INDEX
    Explanations

    sentences that involve user-centric language, particularly referring to the audience as "you."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalTable
    -0.67
    onalds
    -0.63
     Mazar
    -0.58
     חיצוניים
    -0.58
    umab
    -0.57
    saraba
    -0.57
    adda
    -0.56
     Tats
    -0.55
    ształ
    -0.54
     réelle
    -0.53
    POSITIVE LOGITS
    +:+
    0.65
     Chwiliwch
    0.55
    جغرافيا
    0.55
     TQ
    0.54
    xaml
    0.51
     onAnimation
    0.49
    brium
    0.47
    writeField
    0.47
     Stedman
    0.47
    __);
    0.44
    Act Density 0.213%

    No Known Activations