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

    Neuronpedia

    INDEX
    Explanations

    references to office spaces and workplaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Offices
    -0.23
     offices
    -0.23
    nt
    -0.18
     office
    -0.18
    +offset
    -0.17
     officer
    -0.17
    lings
    -0.17
    _office
    -0.16
    soever
    -0.16
    nez
    -0.15
    POSITIVE LOGITS
    365
    0.23
    holders
    0.22
     hours
    0.21
    holder
    0.20
    ehler
    0.20
     Hours
    0.19
    -hours
    0.19
     space
    0.19
    bear
    0.19
    hours
    0.19
    Act Density 0.029%

    No Known Activations