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

    Neuronpedia

    INDEX
    Explanations

    words related to technology specifications and details

    oai_token-act-pair · gpt-3.5-turbo

    mentions of systems or events related to technology and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erb
    -0.75
    channelAvailability
    -0.72
    hops
    -0.68
    rouse
    -0.66
    volent
    -0.66
    nels
    -0.64
    Enlarge
    -0.63
    nob
    -0.61
     theirs
    -0.61
    gotten
    -0.60
    POSITIVE LOGITS
     approximately
    0.67
     601
    0.64
     Nov
    0.62
     610
    0.62
     an
    0.60
     Rough
    0.60
     November
    0.58
     Voltage
    0.58
     Exploration
    0.57
     840
    0.57
    Act Density 0.365%

    No Known Activations