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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe involvement in processes or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     winning
    -0.54
     nghĩa
    -0.54
    Flying
    -0.50
    altes
    -0.49
    levis
    -0.49
     walking
    -0.49
     Flying
    -0.49
     Next
    -0.48
    zku
    -0.48
    atürk
    -0.48
    POSITIVE LOGITS
     focusing
    1.44
     specialising
    1.31
     featuring
    1.30
     specializing
    1.30
     focussing
    1.26
     involving
    1.23
     targeting
    1.19
     Focusing
    1.16
    featuring
    1.15
     Featuring
    1.13
    Act Density 0.213%

    No Known Activations