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

    Neuronpedia

    INDEX
    Explanations

    phrases related to finding out information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Crystal
    -0.70
    ortunately
    -0.67
    creation
    -0.61
    illus
    -0.61
    istent
    -0.61
     prototyp
    -0.60
    ataka
    -0.60
    ģĸ
    -0.59
     Antar
    -0.58
    eries
    -0.58
    POSITIVE LOGITS
    ledge
    0.93
     how
    0.93
     about
    0.86
     why
    0.84
    wards
    0.84
     beforehand
    0.79
     aloud
    0.79
     whats
    0.77
     WHY
    0.76
     ABOUT
    0.75
    Act Density 0.031%

    No Known Activations