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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences emphasizing a high level of a specific attribute

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensis
    -0.73
    osal
    -0.72
    olor
    -0.71
    sburgh
    -0.67
    igi
    -0.66
    izational
    -0.66
    onis
    -0.65
    ourses
    -0.65
    iture
    -0.64
    imus
    -0.62
    POSITIVE LOGITS
     unlikely
    0.86
     rare
    0.85
     similar
    0.82
     much
    0.82
     important
    0.81
     different
    0.81
     informative
    0.80
     nice
    0.80
     busy
    0.79
     seldom
    0.79
    Act Density 0.572%

    No Known Activations