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

    Neuronpedia

    INDEX
    Explanations

    mentions of superlatives or the "best" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HAEL
    -0.69
    onda
    -0.62
    404
    -0.61
    IDS
    -0.60
    FontSize
    -0.60
    Rah
    -0.58
    rade
    -0.58
    ="#
    -0.57
    /
    -0.57
    VICE
    -0.56
    POSITIVE LOGITS
     same
    1.29
     opportunity
    1.08
     requisite
    1.08
     utmost
    1.06
     slightest
    1.03
     largest
    1.02
     widest
    1.01
     easiest
    1.00
     highest
    0.99
    same
    0.98
    Act Density 0.134%

    No Known Activations