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

    Neuronpedia

    INDEX
    Explanations

    phrases containing prepositions related to attributes or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.86
    MLLoader
    -0.76
     Monfieur
    -0.74
    IsContent
    -0.67
     iſt
    -0.67
     themſelves
    -0.65
     الاطلاع
    -0.64
     himſelf
    -0.63
     becauſe
    -0.63
     AssemblyCulture
    -0.62
    POSITIVE LOGITS
    with
    0.90
    WITH
    0.86
    ที่มี
    0.80
     with
    0.79
     WITH
    0.77
     With
    0.72
     avec
    0.71
    avec
    0.69
     no
    0.68
    Με
    0.68
    Act Density 0.387%

    No Known Activations