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

    Neuronpedia

    INDEX
    Explanations

    references to comfort or a comfortable environment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "com" which appears frequently throughout various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kubrick
    -0.77
     harbor
    -0.66
     infringing
    -0.65
     Icelandic
    -0.65
     inund
    -0.63
     alarms
    -0.62
     harbour
    -0.62
    uthor
    -0.60
     manuscript
    -0.59
     Michaels
    -0.59
    POSITIVE LOGITS
    ptroller
    1.33
    forts
    1.17
    etary
    1.09
    mented
    1.08
    ittee
    1.06
    meric
    1.04
    frey
    1.02
    rade
    1.02
    ission
    1.00
    Score
    0.98
    Act Density 0.022%

    No Known Activations