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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical data or ranking

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ħ¢
    -0.60
    Ö¼
    -0.59
    cknowled
    -0.59
    ĺħ
    -0.58
    rification
    -0.57
    rame
    -0.57
     limitation
    -0.56
    urated
    -0.56
     Registration
    -0.55
     Feeling
    -0.55
    POSITIVE LOGITS
    bye
    0.85
    onto
    0.83
     toward
    0.81
    against
    0.80
     differently
    0.79
    aneously
    0.77
    izont
    0.76
     towards
    0.76
     against
    0.75
    edly
    0.75
    Act Density 2.262%

    No Known Activations