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

    Neuronpedia

    INDEX
    Explanations

    the start of new sections or significant segments in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.69
     tartalomajánló
    -0.69
     للاسماء
    -0.68
     themſelves
    -0.68
    Diweddarwch
    -0.68
     jScrollPane
    -0.63
     houſe
    -0.63
    huevos
    -0.60
     autant
    -0.59
     présidenti
    -0.59
    POSITIVE LOGITS
     flow
    0.49
    0.49
    "}}>
    0.47
     LayoutInflater
    0.46
    ()));

    0.46
     hasattr
    0.45
     '',

    0.45
    ste
    0.44
    }]

    0.44
    ]")]
    0.44
    Act Density 0.110%
    No Known Activations