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

    Neuronpedia

    INDEX
    Explanations

    multi-word terms related to specific cultural, historical, political, or scientific topics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ials
    -0.92
    iate
    -0.74
    ially
    -0.72
    iary
    -0.70
    owitz
    -0.69
    rador
    -0.65
    ese
    -0.65
    ed
    -0.64
    bows
    -0.64
    ation
    -0.63
    POSITIVE LOGITS
    gets
    0.73
    #$
    0.66
    ãĤ©
    0.65
     Pwr
    0.59
     Staples
    0.59
    ãģķ
    0.58
    pload
    0.56
    ulner
    0.56
     Typhoon
    0.55
    ãĤĬ
    0.54
    Act Density 8.959%

    No Known Activations