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

    Neuronpedia

    INDEX
    Explanations

    references to historical events and places

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation, indicating a focus on completed statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     elbow
    -0.76
     slightest
    -0.74
     instinct
    -0.70
     volley
    -0.70
     glim
    -0.69
    zzle
    -0.69
     silence
    -0.68
     emotion
    -0.68
    plet
    -0.67
     hug
    -0.67
    POSITIVE LOGITS
     Additionally
    1.42
     However
    1.33
     Furthermore
    1.31
     Also
    1.31
     Therefore
    1.24
     Consequently
    1.24
     Moreover
    1.22
     Nevertheless
    1.21
     Later
    1.18
     Similarly
    1.17
    Act Density 0.850%

    No Known Activations