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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a minimum or baseline condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -0.87
     Efq
    -0.78
     Ponta
    -0.72
     Theſe
    -0.72
     XLV
    -0.72
     uſed
    -0.71
     Fik
    -0.70
    toHaveBeenCalled
    -0.69
     Pala
    -0.69
     Jem
    -0.69
    POSITIVE LOGITS
     least
    1.00
    jmniej
    0.89
     atleast
    0.81
    Least
    0.78
     almeno
    0.75
    least
    0.73
     LEAST
    0.72
     Least
    0.69
    testens
    0.69
     zumindest
    0.68
    Act Density 0.073%

    No Known Activations