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

    Neuronpedia

    INDEX
    Explanations

    references to online sources, particularly datasets and URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.89
     '\\;'
    -0.66
    ंदीखरीदारी
    -0.65
    indd
    -0.65
    NameInMap
    -0.65
    basicConfig
    -0.65
    ParallelGroup
    -0.64
    ništ
    -0.64
    jspb
    -0.64
    openqa
    -0.63
    POSITIVE LOGITS
     hobby
    0.60
     lovingly
    0.51
     Enthusi
    0.50
     amateur
    0.48
     Passion
    0.48
     volunteer
    0.47
     homemade
    0.46
     Amateur
    0.45
     Volunteer
    0.45
    passion
    0.45
    Act Density 0.380%

    No Known Activations