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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of items or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Orville
    -0.73
    lüğ
    -0.66
     obicei
    -0.62
     @"";
    -0.62
    k
    -0.62
     DPP
    -0.60
     cemento
    -0.60
     років
    -0.60
     arroz
    -0.59
     Leona
    -0.58
    POSITIVE LOGITS
     CONTAIN
    1.66
     Contain
    1.65
     contains
    1.52
     contain
    1.50
     contained
    1.47
     Contains
    1.47
     enthalten
    1.33
     Containing
    1.33
    Contain
    1.31
    contain
    1.30
    Act Density 0.102%

    No Known Activations