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

    Neuronpedia

    INDEX
    Explanations

    adjectives and phrases related to characteristics and behaviors, such as optimism, elegance, and relentlessness

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    slave
    -0.79
    ainer
    -0.77
    Ĥİ
    -0.77
    ploma
    -0.74
    orah
    -0.74
    OIL
    -0.73
    uther
    -0.72
    udder
    -0.72
    avers
    -0.71
    ittee
    -0.70
    POSITIVE LOGITS
    ness
    1.33
    ly
    1.23
    nesses
    1.11
     nature
    1.05
     sounding
    0.99
     ones
    0.95
     minded
    0.92
    glers
    0.91
    NESS
    0.91
     souls
    0.91
    Act Density 3.889%

    No Known Activations