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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical locations or configurations, often involving technical or mechanical elements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating locations or contexts within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HAEL
    -0.68
     presided
    -0.66
    Reason
    -0.65
    ril
    -0.63
     Revision
    -0.62
     Juda
    -0.61
     includ
    -0.61
    REF
    -0.61
     AUTHOR
    -0.61
    llor
    -0.61
    POSITIVE LOGITS
     lieu
    1.38
     conjunction
    1.25
    effic
    1.21
     emergencies
    1.13
    efficiency
    1.13
    versions
    1.12
     situations
    1.09
    animate
    1.08
     unison
    1.08
     accordance
    1.07
    Act Density 0.297%

    No Known Activations