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

    Neuronpedia

    INDEX
    Explanations

    phrases related to empowerment and leadership

    oai_token-act-pair · gpt-3.5-turbo

    ingredients and quantities in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ))))
    -0.77
    .).
    -0.75
    etheless
    -0.72
    .''.
    -0.71
     sqor
    -0.71
    ''.
    -0.69
    ãĤ´ãĥ³
    -0.68
    }.
    -0.66
    soType
    -0.66
    Conclusion
    -0.66
    POSITIVE LOGITS
     neighbour
    0.54
     physical
    0.54
     jew
    0.52
     pupil
    0.52
     youths
    0.51
     pupils
    0.50
     labou
    0.50
     boys
    0.49
     centrif
    0.48
     machines
    0.48
    Act Density 2.030%

    No Known Activations