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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptions or exclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.94
    ocarditis
    -0.91
    OGND
    -0.82
    dotenv
    -0.80
    
    -0.75
    躇
    -0.72
    évaluateur
    -0.71
    ScopeManager
    -0.71
    ServiceClient
    -0.70
    ukunft
    -0.68
    POSITIVE LOGITS
     except
    1.32
    Except
    1.28
     Except
    1.22
    except
    1.16
     unless
    1.01
     excepto
    0.98
    unless
    0.94
     EXCEPT
    0.90
    EXCEPT
    0.86
     außer
    0.85
    Act Density 0.064%

    No Known Activations