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

    Neuronpedia

    INDEX
    Explanations

    movie or song titles

    oai_token-act-pair · gpt-3.5-turbo

    titles of songs or movies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.72
     estimating
    -0.65
    surprisingly
    -0.63
     subdiv
    -0.62
     pci
    -0.60
     assessing
    -0.60
     varied
    -0.59
     biomedical
    -0.59
     respondents
    -0.58
     specifying
    -0.58
    POSITIVE LOGITS
    ")
    1.85
    ").
    1.78
    "),
    1.72
    ",
    1.65
    %"
    1.64
    "]
    1.63
    "?
    1.63
    "
    1.62
    .")
    1.61
    "!
    1.61
    Act Density 0.353%

    No Known Activations