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

    Neuronpedia

    INDEX
    Explanations

    terms associated with agreements or disputes involving "with"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     …
    -0.52
     who
    -0.47
     group
    -0.44
     H
    -0.44
     in
    -0.43
    тин
    -0.42
    onView
    -0.42
    soort
    -0.42
     we
    -0.41
     en
    -0.41
    POSITIVE LOGITS
     Monfieur
    1.00
     myſelf
    0.95
     Houſe
    0.93
     againſt
    0.87
     Efq
    0.87
     Anſ
    0.86
     himſelf
    0.83
     AssemblyCompany
    0.83
    ſelf
    0.83
     Majefty
    0.83
    Act Density 0.276%

    No Known Activations