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

    Neuronpedia

    INDEX
    Explanations

    mentions of violent actions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or ethical concerns related to actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quartered
    -0.61
    anan
    -0.54
    xtap
    -0.53
    doi
    -0.51
     largeDownload
    -0.51
    uscript
    -0.49
    antine
    -0.47
    heastern
    -0.46
    iple
    -0.46
     Gallup
    -0.46
    POSITIVE LOGITS
    )).
    0.95
    ?".
    0.91
    )),
    0.83
    ?).
    0.83
    ?",
    0.82
    )?
    0.79
     anymore
    0.79
    "))
    0.74
    ))
    0.74
    ?),
    0.71
    Act Density 1.849%

    No Known Activations