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

    Neuronpedia

    INDEX
    Explanations

    references to social media and its impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĥ½
    -5.76
    ²
    -5.58
    ¾
    -5.49
           ↵
    -5.46
    <|outofrange|>
    -5.46
     ↵
    -5.46
    ↵↵
    -5.46
    -5.46
    <|outofrange|>
    -5.46
    ↵
    -5.46
    POSITIVE LOGITS
    OTE
    1.93
    rior
    1.86
     notices
    1.64
    emon
    1.62
    acker
    1.60
     link
    1.52
    uncher
    1.52
    ookie
    1.51
     alerts
    1.50
    ijer
    1.49
    Act Density 0.513%

    No Known Activations