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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "/>
    -0.88
    '/>
    -0.87
    "/>
    -0.85
    }}/>
    -0.85
    .')
    -0.81
    }/>
    -0.80
    .")
    -0.78
    ')}}"
    -0.77
    '));
    -0.76
    .');
    -0.74
    POSITIVE LOGITS
    ):
    2.08
    "):
    1.96
    ]:
    1.87
    '):
    1.86
    ）：
    1.80
    ”:
    1.80
    ']:
    1.77
    ":
    1.77
    "]:
    1.74
    }):
    1.68
    Act Density 0.995%

    No Known Activations