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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating separation or distinction within categories or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DebuggerNonUser
    -0.63
    Lähteet
    -0.62
     endforeach
    -0.61
     Siti
    -0.55
    InjectAttribute
    -0.54
    AndPassword
    -0.54
     onData
    -0.54
     JAXBElement
    -0.54
    PDOException
    -0.53
     timelapse
    -0.53
    POSITIVE LOGITS
     separate
    1.26
    separate
    1.18
    Separate
    1.06
     Separate
    1.00
     terpisah
    0.98
     separately
    0.97
     seperate
    0.96
     SEPAR
    0.93
     separado
    0.89
     standalone
    0.83
    Act Density 0.337%

    No Known Activations