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

    Neuronpedia

    INDEX
    Explanations

    words related to businesses or organizations

    oai_token-act-pair · gpt-3.5-turbo

    words related to communities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     regard
    -0.65
    uthor
    -0.63
     infringing
    -0.61
     gratification
    -0.61
     existence
    -0.60
     wonders
    -0.58
     commencement
    -0.57
     defiant
    -0.56
     regards
    -0.56
     preference
    -0.55
    POSITIVE LOGITS
    forts
    1.36
    ptroller
    1.20
    ission
    1.09
    frey
    1.06
    pton
    1.02
    etary
    0.99
    plement
    0.99
    fy
    0.98
    meric
    0.97
    anche
    0.96
    Act Density 0.022%

    No Known Activations