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

    Neuronpedia

    INDEX
    Explanations

    numerical data and categories associated with exceptions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.56
    GrantedAuthority
    -0.55
     '\\;'
    -0.52
    Ligações
    -0.52
    CADE
    -0.50
    GEBURTS
    -0.49
    InputBorder
    -0.48
    ()}>
    -0.48
    őbb
    -0.48
    出版年
    -0.48
    POSITIVE LOGITS
     except
    0.70
     excepting
    0.66
     exception
    0.65
    Except
    0.65
     excepto
    0.63
     GenerationType
    0.62
    LookAnd
    0.61
    except
    0.61
     but
    0.60
     Except
    0.60
    Act Density 0.265%

    No Known Activations