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

    Neuronpedia

    INDEX
    Explanations

    mentions of significant aspects or developments

    oai_token-act-pair · gpt-3.5-turbo

    phrases or constructs that involve the word "the" and highlight significant features or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ago
    -0.79
    hei
    -0.74
    hops
    -0.71
    ho
    -0.69
    airs
    -0.69
    SEA
    -0.68
    aho
    -0.68
    fw
    -0.68
    ishers
    -0.67
    γ
    -0.67
    POSITIVE LOGITS
     slightest
    1.03
     inability
    1.00
     sheer
    0.99
     emergence
    0.98
     presence
    0.93
     extent
    0.89
     tendency
    0.88
     lack
    0.88
     possibility
    0.87
     resultant
    0.86
    Act Density 0.147%

    No Known Activations