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

    Neuronpedia

    INDEX
    Explanations

    words related to long-term activities or processes

    oai_token-act-pair · gpt-3.5-turbo

    topics related to safety, particularly concerning personal and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OULD
    -0.75
    hod
    -0.61
    umbledore
    -0.59
    ))))
    -0.59
    ERE
    -0.58
     {:
    -0.57
    =~
    -0.57
    )))
    -0.56
    rame
    -0.55
    pload
    -0.55
    POSITIVE LOGITS
     lately
    2.05
     since
    1.97
    since
    1.64
     ever
    1.35
     recently
    1.21
     thus
    1.05
     Since
    1.05
    Since
    1.03
     recent
    0.96
     over
    0.95
    Act Density 0.929%

    No Known Activations