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

    Neuronpedia

    INDEX
    Explanations

    connections involving conjunctions and relational phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.70
     a
    -0.60
    <eos>
    -0.58
     (
    -0.55
     the
    -0.53
    ...
    -0.53
    ,
    -0.51
     an
    -0.51
    …
    -0.49
     No
    -0.49
    POSITIVE LOGITS
     Theſe
    1.00
     ―――――
    0.97
     Houſe
    0.96
    ✨:
    0.93
     Reſ
    0.90
     Anſ
    0.89
     houſe
    0.89
     photolibrary
    0.89
    ########.
    0.87
     ainfi
    0.87
    Act Density 0.276%

    No Known Activations