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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something is evident or clearly understood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]));
    -0.40
    CloseOperation
    -0.39
    writerow
    -0.36
    !*\
    -0.35
     Exchange
    -0.35
    ()));
    -0.35
     sele
    -0.34
     exchange
    -0.34
     createStore
    -0.33
     stores
    -0.33
    POSITIVE LOGITS
     obvious
    1.53
    obvious
    1.52
    Obvious
    1.50
     obvio
    1.16
     évident
    1.13
    VIOUS
    1.09
     evident
    1.02
    obviously
    0.99
    evident
    0.99
     obviously
    0.97
    Act Density 0.300%

    No Known Activations