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

    Neuronpedia

    INDEX
    Explanations

    words related to sports and politics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃŁ
    -0.69
     Feder
    -0.68
     Frey
    -0.64
     FIR
    -0.61
     Manufact
    -0.60
     Berman
    -0.60
     Federation
    -0.59
    Ey
    -0.59
     Brunswick
    -0.58
     oneself
    -0.58
    POSITIVE LOGITS
    worthiness
    1.00
     predicament
    0.92
    fulness
    0.92
    iness
    0.89
    lessness
    0.88
     prowess
    0.85
    ability
    0.85
     abilities
    0.82
    abilities
    0.79
     woes
    0.79
    Act Density 0.504%

    No Known Activations