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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to data usage and technology

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
    ©¶æ¥µ
    -0.63
     practition
    -0.63
    GGGGGGGG
    -0.59
     citiz
    -0.57
    ña
    -0.57
    URA
    -0.56
    ensical
    -0.55
    PsyNetMessage
    -0.55
    gdala
    -0.54
    POSITIVE LOGITS
    Rot
    0.58
    cs
    0.57
    itiveness
    0.57
    ï¸ı
    0.56
    hare
    0.55
    izont
    0.52
    rimp
    0.52
    alion
    0.52
     LLP
    0.51
    spin
    0.51
    Act Density 0.872%

    No Known Activations