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

    Neuronpedia

    INDEX
    Explanations

    information related to news events and statements made by individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Wikipedia
    -0.65
     Schedule
    -0.61
    Minecraft
    -0.61
    acea
    -0.60
     Dating
    -0.59
     Wikipedia
    -0.58
     (%)
    -0.58
    à¨
    -0.56
    aceae
    -0.55
     TAMADRA
    -0.55
    POSITIVE LOGITS
    cerning
    0.80
    icter
    0.78
    ascript
    0.77
    lement
    0.74
    leases
    0.74
    iott
    0.70
    VICE
    0.68
    resso
    0.67
    ioch
    0.67
    remlin
    0.65
    Act Density 0.176%

    No Known Activations