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

    Neuronpedia

    INDEX
    Explanations

    specific phrases related to legal documents or official responses

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbm
    -0.83
    wic
    -0.83
    gdala
    -0.81
    quished
    -0.79
    kees
    -0.78
    addon
    -0.76
    odcast
    -0.74
    ixel
    -0.74
    married
    -0.74
    ecast
    -0.74
    POSITIVE LOGITS
     creativity
    1.24
     decency
    1.16
     professionalism
    1.14
     sophistication
    1.11
     resilience
    1.11
     cohesion
    1.10
     responsiveness
    1.10
     openness
    1.09
     generosity
    1.09
     degradation
    1.08
    Act Density 2.255%

    No Known Activations