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

    Neuronpedia

    INDEX
    Explanations

    words related to news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Other," indicating a focus on additional or alternative items or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opus
    -0.73
    iasis
    -0.68
    ocracy
    -0.64
    ossession
    -0.63
    vet
    -0.62
     Hussein
    -0.62
    ony
    -0.61
    opoly
    -0.60
    Always
    -0.59
    '"
    -0.59
    POSITIVE LOGITS
    worldly
    1.54
    quickShipAvailable
    1.05
     notable
    1.03
    wise
    1.02
     aspects
    0.89
     factors
    0.88
     noteworthy
    0.84
     examples
    0.82
    where
    0.81
     considerations
    0.79
    Act Density 0.065%

    No Known Activations