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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strong recommendations or advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    evin
    -0.14
    673
    -0.14
     thanking
    -0.13
    aversable
    -0.12
    xdd
    -0.12
    ãĥ«ãĥķ
    -0.12
    lue
    -0.12
    -notification
    -0.12
    inheritDoc
    -0.12
    cia
    -0.12
    POSITIVE LOGITS
     recommendation
    0.98
     recommend
    0.92
     recommendations
    0.91
     recommended
    0.88
    recommend
    0.86
    Recommend
    0.84
     recommends
    0.83
     recommending
    0.79
     Recommendation
    0.79
    recommended
    0.78
    Act Density 0.683%

    No Known Activations