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

    Neuronpedia

    INDEX
    Explanations

    references to social issues and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.50
     OMITBAD
    -0.48
     Italijanski
    -0.44
    RTCK
    -0.43
    DebuggerNonUser
    -0.43
    webElementXpaths
    -0.42
    QMetaType
    -0.40
    stdc
    -0.40
    tableCell
    -0.38
    ArrowToggle
    -0.37
    POSITIVE LOGITS
     here
    4.53
     aquí
    3.39
    here
    3.36
     Here
    3.19
     здесь
    3.14
    Here
    3.13
     aqui
    2.95
     هنا
    2.88
     ici
    2.86
     HERE
    2.84
    Act Density 3.983%

    No Known Activations