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

    Neuronpedia

    INDEX
    Explanations

    instances of different types of brackets and quotes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hu
    -0.65
     Nakamura
    -0.64
    CascadeType
    -0.62
     plate
    -0.60
     damn
    -0.60
     Rah
    -0.60
    stdc
    -0.60
    emos
    -0.59
    card
    -0.58
     הט
    -0.57
    POSITIVE LOGITS
    ]")]
    1.52
    }")]
    1.43
    .")]
    1.38
    __':
    1.27
    __":
    1.25
    ")]
    1.16
    .*")]
    1.16
    )";
    1.16
    })));
    1.14
    ])));
    1.14
    Act Density 0.028%

    No Known Activations